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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6636
    Prev
    Next
    INDEX
    Explanations

    words related to fashion items and accessories, particularly shoes and watches

    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
    68
    +0.15
    0.8%
    1983
    +0.14
    0.7%
    1233
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.15
    0.06
    1233
    +0.14
    0.05
    68
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.50
     nõ
    -0.89
    AutoScaleMode
    -0.80
     mitte
    -0.78
     väga
    -0.71
     võimal
    -0.69
     inimes
    -0.68
    rifuge
    -0.68
    ContentAlignment
    -0.67
     lõ
    -0.67
    POSITIVE LOGITS
     maneu
    1.57
     roberto
    1.43
     impra
    1.40
     affor
    1.39
     increa
    1.35
     alberto
    1.33
     ricardo
    1.33
     indestru
    1.32
     jorge
    1.31
     excru
    1.31
    Activations Density 0.539%

    No Known Activations