© 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. 1-RES-JB
    11. 3144
    Prev
    Next
    INDEX
    Explanations

    words related to evidence or proving something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "proof"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.67
    NW
    -0.65
    ades
    -0.64
    NetMessage
    -0.64
    iewicz
    -0.63
    artney
    -0.62
    avy
    -0.61
    phrine
    -0.61
    thus
    -0.59
     Minor
    -0.59
    POSITIVE LOGITS
     proof
    1.34
     proofs
    1.20
     Proof
    1.05
    Proof
    0.97
    proof
    0.97
    ificate
    0.88
    reading
    0.81
     proving
    0.80
    ĸļ
    0.77
     proves
    0.75
    Activations Density 0.008%

    No Known Activations