© 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. 4-RES-JB
    11. 24067
    Prev
    Next
    INDEX
    Explanations

    names or terms associated with individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities, particularly those with the prefix "Mc" or similar

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

    No Comments

    Negative Logits
     Croatian
    -0.73
    ursday
    -0.68
     Ae
    -0.67
     Camer
    -0.63
     Bulgar
    -0.62
    uesday
    -0.61
     Galileo
    -0.59
     Ramadan
    -0.59
     Piercing
    -0.58
     ATM
    -0.58
    POSITIVE LOGITS
    cheon
    0.94
    issance
    0.85
    adows
    0.84
    neys
    0.83
    ney
    0.81
    intosh
    0.81
    enzie
    0.80
    uliffe
    0.79
    yre
    0.78
    roth
    0.77
    Activations Density 0.064%

    No Known Activations