© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2841
    Prev
    Next
    INDEX
    Explanations

    words indicating importance or influence in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "instrumental" and related terms conveying support or influence

    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
    than
    -0.79
     Wilde
    -0.78
    lust
    -0.70
    room
    -0.68
    ukemia
    -0.68
     Wonderland
    -0.67
    Flo
    -0.67
    arent
    -0.65
     Leopard
    -0.65
    liness
    -0.65
    POSITIVE LOGITS
     instrumental
    0.98
    ised
    0.86
    ãĥŁ
    0.85
    tarian
    0.84
    tarians
    0.84
    ized
    0.84
    arial
    0.84
    izes
    0.83
    strument
    0.83
     incent
    0.82
    Activations Density 0.008%

    No Known Activations