© 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. 1-RES-JB
    11. 16212
    Prev
    Next
    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the locations Mesa and Plymouth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gey
    -0.81
     Gord
    -0.73
     benefic
    -0.72
    ifiable
    -0.71
     nerv
    -0.70
    uary
    -0.69
     strat
    -0.68
    phabet
    -0.64
     precip
    -0.64
     tang
    -0.63
    POSITIVE LOGITS
    sterdam
    0.78
    ãĤ¨ãĥ«
    0.73
    lished
    0.73
    ãĥ¼ãĥ³
    0.72
    pered
    0.72
    Featured
    0.72
    ãĥ¼ãĥĨãĤ£
    0.71
    conservancy
    0.71
    âķ
    0.70
    tek
    0.68
    Activations Density 0.030%

    No Known Activations