© 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 EvalsExportsinterp-engineNEWAPI 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. 15172
    Prev
    Next
    INDEX
    Explanations

    mentions of full-time work

    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
    1013
    +0.10
    0.3%
    674
    +0.10
    0.3%
    168
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.10
    0.02
    1492
    +0.10
    0.02
    1081
    +0.10
    0.02
    Negative Logits
     increa
    -1.54
     effe
    -1.43
     thut
    -1.42
     inev
    -1.40
     nece
    -1.39
     unden
    -1.39
     accla
    -1.35
     volunte
    -1.34
     impra
    -1.32
     affor
    -1.31
    POSITIVE LOGITS
    <bos>
    0.95
    time
    0.73
    ruly
    0.72
    mistak
    0.71
     time
    0.70
    sightly
    0.66
    relenting
    0.65
    OGND
    0.65
     Time
    0.64
    yelitis
    0.63
    Activations Density 0.091%

    No Known Activations