© 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. 7622
    Prev
    Next
    INDEX
    Explanations

    pieces of code or technical information

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and code syntax in advertisements

    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
    cker
    -0.69
    cham
    -0.65
    cha
    -0.60
    wards
    -0.60
    ball
    -0.59
    warts
    -0.58
     Syndicate
    -0.58
    geist
    -0.58
    ensical
    -0.56
    giving
    -0.56
    POSITIVE LOGITS
    veyard
    0.79
    istar
    0.75
     ..........
    0.74
    ï¸
    0.73
     Carbuncle
    0.70
    soDeliveryDate
    0.68
    allery
    0.67
    ¯¯¯¯¯¯¯¯
    0.65
    utherford
    0.64
    icut
    0.64
    Activations Density 0.016%

    No Known Activations