© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17101
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names and places

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tom" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shapeshifter
    -0.76
    uckland
    -0.67
    draft
    -0.66
    UID
    -0.66
    journal
    -0.65
     Gazette
    -0.65
    UGE
    -0.64
    cens
    -0.63
    heid
    -0.63
    gypt
    -0.61
    POSITIVE LOGITS
    atoes
    1.08
    my
    1.06
    Tom
    1.02
    orrow
    1.00
    othy
    0.98
    atis
    0.98
    tom
    0.96
    itan
    0.95
    atsu
    0.93
    asso
    0.92
    Activations Density 0.005%

    No Known Activations