© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1792
    Prev
    Next
    INDEX
    Explanations

    actions or behaviors that involve physical interaction or engagement

    oai_token-act-pair · gpt-3.5-turbo

    actions or behaviors that indicate negative or confrontational situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    si
    -0.86
    eria
    -0.77
    antha
    -0.72
    see
    -0.72
    chev
    -0.70
    skin
    -0.68
    word
    -0.67
    tes
    -0.67
    nings
    -0.66
    ère
    -0.66
    POSITIVE LOGITS
     oneself
    1.15
     yourself
    0.94
     accordingly
    0.81
    redients
    0.77
     ourselves
    0.76
     noises
    0.76
     hearts
    0.73
     yourselves
    0.73
     engagements
    0.72
     idiots
    0.71
    Activations Density 0.313%

    No Known Activations