© 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. 6-RES-JB
    11. 1623
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    key geographical and political terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initions
    -0.77
    iage
    -0.70
    insula
    -0.70
    ortment
    -0.68
    robe
    -0.64
    enery
    -0.64
    lihood
    -0.62
     constitution
    -0.61
    etsk
    -0.61
    rity
    -0.61
    POSITIVE LOGITS
    isible
    0.92
    arily
    0.88
    worthy
    0.83
    vable
    0.82
     incarn
    0.81
    eligible
    0.80
    actly
    0.79
    centric
    0.79
    ishly
    0.79
    ivable
    0.79
    Activations Density 0.444%

    No Known Activations