© 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. 8-RES-JB
    11. 7635
    Prev
    Next
    INDEX
    Explanations

    places where people are moving from or to

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or origins of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faced
    -0.84
    ema
    -0.79
    idav
    -0.79
    stakes
    -0.77
    natureconservancy
    -0.77
    etary
    -0.76
    flex
    -0.75
    attribute
    -0.75
    rils
    -0.75
    gradation
    -0.74
    POSITIVE LOGITS
     whence
    1.23
     afar
    1.09
     abroad
    1.02
     thence
    0.85
     elsewhere
    0.83
     overseas
    0.80
     somewhere
    0.78
     Trinidad
    0.77
     Spain
    0.77
     Amsterdam
    0.77
    Activations Density 0.104%

    No Known Activations