© 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. 0-RES-JB
    11. 4082
    Prev
    Next
    INDEX
    Explanations

    phrases with colons followed by an emphasis or highlighting

    oai_token-act-pair · gpt-3.5-turbo

    colons or specific segments that present detailed or categorical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.72
    mercial
    -0.60
    itially
    -0.57
    uably
    -0.56
    sbm
    -0.56
    oided
    -0.55
    sembly
    -0.55
    athered
    -0.55
    ancial
    -0.54
    olicy
    -0.54
    POSITIVE LOGITS
    :
    2.17
    !:
    1.53
    :[
    1.51
    :"
    1.50
    :-
    1.49
    :(
    1.48
    ?:
    1.46
    .:
    1.46
    *:
    1.45
    :'
    1.40
    Activations Density 0.165%

    No Known Activations