© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 266
    Prev
    Next
    INDEX
    Explanations

    words related to customer feedback and opinion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    680
    +0.10
    0.3%
    900
    +0.08
    0.2%
    896
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.10
    0.02
    1150
    +0.08
    0.01
    1896
    +0.08
    0.01
    Negative Logits
     look
    -0.75
    듦
    -0.73
    push
    -0.70
     im
    -0.70
     si
    -0.70
     off
    -0.69
    call
    -0.69
     call
    -0.69
    XtraEditors
    -0.68
    off
    -0.68
    POSITIVE LOGITS
     increa
    2.45
     Respondents
    2.43
     impra
    2.29
     strick
    2.25
     maneu
    2.25
     respondent
    2.23
     fortn
    2.22
     Respondent
    2.20
     volunte
    2.15
     affor
    2.14
    Activations Density 0.242%

    No Known Activations