© 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. 442
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "Len"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Len" and its variations

    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
     Occupations
    -0.70
     Typhoon
    -0.67
    xual
    -0.67
    FUL
    -0.64
    worldly
    -0.63
     Seeking
    -0.62
    AGES
    -0.62
    CLASSIFIED
    -0.60
    tale
    -0.60
    ر
    -0.59
    POSITIVE LOGITS
    iency
    1.02
    ovo
    1.00
    essee
    0.96
    uci
    0.94
    opoly
    0.86
    ikuman
    0.85
    apse
    0.84
    unci
    0.83
    apses
    0.82
    seys
    0.82
    Activations Density 0.010%

    No Known Activations