© 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. 10247
    Prev
    Next
    INDEX
    Explanations

    words related to requirements or necessary actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "require" in various contexts

    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
    ight
    -0.74
    ship
    -0.70
     Tide
    -0.70
    kind
    -0.68
     Bom
    -0.68
     Sounds
    -0.65
     Babe
    -0.65
     Airways
    -0.63
    bench
    -0.63
    stream
    -0.63
    POSITIVE LOGITS
    lessly
    0.84
    MENTS
    0.79
     compromising
    0.79
     compromises
    0.76
     undue
    0.73
    require
    0.73
     costly
    0.72
    ered
    0.72
     patience
    0.72
    enei
    0.72
    Activations Density 0.036%

    No Known Activations