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. 140
    Prev
    Next
    INDEX
    Explanations

    information related to events, such as event details, scheduling, and organization instructions

    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
    50
    +0.20
    1.3%
    1870
    +0.10
    0.7%
    1392
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1634
    +0.20
    0.04
    25
    +0.10
    0.04
    1392
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.64
    <?
    -0.76
    ⓧ
    -0.73
    HasAnnotation
    -0.72
     onResume
    -0.67
    public
    -0.67
    lateinit
    -0.66
    const
    -0.66
    /*++
    -0.66
    Hochspringen
    -0.63
    POSITIVE LOGITS
     bandung
    1.57
     Minang
    1.53
     Juf
    1.52
     maroc
    1.51
     wien
    1.51
     affor
    1.49
     fta
    1.47
     unlaw
    1.47
     maneu
    1.47
     casio
    1.46
    Activations Density 0.098%

    No Known Activations