© 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. 19657
    Prev
    Next
    INDEX
    Explanations

    names of specific geographical locations and political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or regional identities

    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
    notation
    -0.84
    naissance
    -0.82
    ©¶æ
    -0.82
    vernment
    -0.79
    phrine
    -0.74
    gee
    -0.69
    claimed
    -0.68
    ERC
    -0.68
    ZA
    -0.68
    notations
    -0.67
    POSITIVE LOGITS
    sburgh
    1.06
    inx
    0.98
    onia
    0.93
    sburg
    0.85
    ydia
    0.82
    aji
    0.81
    enger
    0.78
    downs
    0.78
    antine
    0.76
    uci
    0.74
    Activations Density 0.053%

    No Known Activations