© 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. 20050
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges and problems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to challenges and obstacles

    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
    inav
    -0.76
    elin
    -0.73
    psc
    -0.71
    rocal
    -0.71
    liv
    -0.71
    cffff
    -0.69
    lys
    -0.69
    asty
    -0.68
    rams
    -0.67
    idine
    -0.66
    POSITIVE LOGITS
     plag
    0.85
     facing
    0.78
     imaginable
    0.76
     confronting
    0.75
     motivating
    0.66
     contributor
    0.66
    Article
    0.65
     hind
    0.64
     hurdle
    0.64
     separating
    0.64
    Activations Density 0.206%

    No Known Activations