© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13762
    Prev
    Next
    INDEX
    Explanations

    long descriptions of physical appearance

    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
    1385
    +0.11
    0.3%
    736
    +0.10
    0.3%
    964
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.11
    0.04
    1906
    +0.10
    0.02
    1818
    +0.09
    0.04
    Negative Logits
     Cfr
    -1.16
     allarg
    -1.12
     dises
    -1.12
     squa
    -1.10
     embra
    -1.08
     socie
    -1.08
     wien
    -1.04
     haup
    -1.04
     Simult
    -1.03
     bordeaux
    -1.03
    POSITIVE LOGITS
     hair
    0.96
    hair
    0.74
    <bos>
    0.69
     hairstyle
    0.69
     Hair
    0.68
    Hair
    0.68
    haired
    0.64
     tóc
    0.64
     HAIR
    0.59
     hairs
    0.58
    Activations Density 0.155%

    No Known Activations