Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5401
    Prev
    Next
    INDEX
    Explanations

    names, particularly with a focus on surnames

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1994
    +0.15
    0.9%
    1406
    +0.14
    0.8%
    1133
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1994
    +0.15
    0.06
    1256
    +0.14
    0.05
    1343
    +0.14
    0.07
    Negative Logits
    <bos>
    -1.45
     intersper
    -1.35
     apprehen
    -1.06
     unspeak
    -1.02
     encomp
    -1.02
     shenan
    -1.00
     vainly
    -0.97
     disagre
    -0.94
     trod
    -0.93
     quitted
    -0.92
    POSITIVE LOGITS
    Hy
    1.02
     Gy
    0.99
     Ty
    0.97
     Hy
    0.97
    hy
    0.97
     Wy
    0.96
     Dy
    0.95
     dy
    0.94
    Ly
    0.93
     hy
    0.93
    Activations Density 0.568%

    No Known Activations