© 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. 8613
    Prev
    Next
    INDEX
    Explanations

    numbers or words indicating a position of being first or ahead

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ahead."

    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
     mart
    -0.75
    pmwiki
    -0.69
    cci
    -0.68
    è¦ļéĨĴ
    -0.67
    rug
    -0.66
    gran
    -0.66
    zip
    -0.65
    VID
    -0.65
    xx
    -0.64
    mini
    -0.64
    POSITIVE LOGITS
    itism
    0.79
    manship
    0.75
    taining
    0.75
     ahead
    0.71
    noon
    0.71
     theirs
    0.67
    wards
    0.66
    itives
    0.66
     hers
    0.66
    selling
    0.66
    Activations Density 0.009%

    No Known Activations