© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6991
    Prev
    Next
    INDEX
    Explanations

    phrases indicating belief, suspicion, or thoughts about certain events or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investigations and beliefs in evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gard
    -0.78
    mbuds
    -0.76
    dyl
    -0.76
    limits
    -0.72
     wonders
    -0.72
     decree
    -0.65
     obser
    -0.65
     Needless
    -0.63
    ruciating
    -0.63
    Dialog
    -0.63
    POSITIVE LOGITS
     belonged
    1.01
     belong
    0.93
    arnaev
    0.83
     belonging
    0.79
     abducted
    0.75
     belongs
    0.75
     originated
    0.75
     foul
    0.74
     arson
    0.73
     Paddock
    0.72
    Activations Density 0.262%

    No Known Activations