© 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. 20133
    Prev
    Next
    INDEX
    Explanations

    bits of code or technical terms like arrays, layers, protocols, and records

    oai_token-act-pair · gpt-3.5-turbo

    references to new concepts, ideas, or developments

    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
    otal
    -0.74
    akespeare
    -0.67
    vag
    -0.67
    anuts
    -0.63
    ealous
    -0.59
    formance
    -0.56
    aceae
    -0.56
    enged
    -0.55
    indu
    -0.55
    ccoli
    -0.55
    POSITIVE LOGITS
     arrivals
    0.81
     hires
    0.77
     entrants
    0.75
    anding
    0.75
     paradigm
    0.73
     additions
    0.73
    stadt
    0.70
     architectures
    0.68
     hire
    0.68
     Dino
    0.66
    Activations Density 0.419%

    No Known Activations