© 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. 7-RES-JB
    11. 21543
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people or characters, likely from a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    instances of prominent characters or names within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancial
    -0.92
    committee
    -0.80
     merit
    -0.79
     declass
    -0.78
    Senate
    -0.77
    icultural
    -0.75
     divest
    -0.74
    Congress
    -0.71
    ements
    -0.71
    iners
    -0.71
    POSITIVE LOGITS
     Totem
    0.88
     Wand
    0.85
     whom
    0.84
     Healer
    0.83
     Cunning
    0.82
     Tooth
    0.82
     Bunny
    0.82
     Zoro
    0.79
     Crush
    0.78
     Beauty
    0.77
    Activations Density 0.482%

    No Known Activations