© 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. 8-RES-JB
    11. 6908
    Prev
    Next
    INDEX
    Explanations

    common verbs relating to naming or identifying

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving naming or identifying multiple items or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entimes
    -0.78
     tempered
    -0.76
    fortune
    -0.69
    fulness
    -0.66
     childbirth
    -0.66
    ful
    -0.65
    fully
    -0.64
    tails
    -0.64
    tail
    -0.64
    nw
    -0.63
    POSITIVE LOGITS
     culprit
    1.09
     perpetrators
    0.90
     Cosponsors
    0.79
     perpetrator
    0.77
     specific
    0.77
     è£ıè
    0.77
     genus
    0.74
     NCT
    0.73
     suspects
    0.73
     winners
    0.73
    Activations Density 0.392%

    No Known Activations