© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5834
    Prev
    Next
    INDEX
    Explanations

    errors in writing, such as spelling and grammar mistakes, in job applications and CVs, along with recommendations for avoiding them

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1150
    +0.09
    0.3%
    1593
    +0.08
    0.2%
    1403
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.09
    0.03
    1553
    +0.08
    0.05
    95
    +0.08
    0.02
    Negative Logits
     nuage
    -0.61
    addContainer
    -0.60
    })*/
    -0.58
    marginHorizontal
    -0.58
     dichi
    -0.57
     grammi
    -0.57
    marginVertical
    -0.56
     nephe
    -0.55
    perPage
    -0.55
    };*/
    -0.55
    POSITIVE LOGITS
     audition
    0.86
     auditions
    0.75
     interview
    0.67
     recruiters
    0.67
     candidacy
    0.67
     interviewers
    0.66
     applicants
    0.65
     recruiter
    0.65
     applicant
    0.65
     candidate
    0.61
    Activations Density 0.426%

    No Known Activations