© 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. 6406
    Prev
    Next
    INDEX
    Explanations

    commands or instructions being given or received

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating communication or information exchange.

    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
    cv
    -0.76
    uded
    -0.72
    alach
    -0.70
    wx
    -0.69
    til
    -0.67
    agos
    -0.66
    malink
    -0.66
    usat
    -0.66
    LGBT
    -0.64
    respective
    -0.64
    POSITIVE LOGITS
     him
    0.81
     me
    0.75
     politely
    0.70
     paramedics
    0.68
     kindly
    0.66
     us
    0.65
     them
    0.65
     Mahjong
    0.64
     angrily
    0.64
     '[
    0.64
    Activations Density 0.304%

    No Known Activations