© 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. 6-RES-JB
    11. 9897
    Prev
    Next
    INDEX
    Explanations

    names or parts of names with the letters "ste" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Ste" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailability
    -0.76
     scant
    -0.69
     concess
    -0.65
    iannopoulos
    -0.63
    ecause
    -0.62
     substance
    -0.60
    ELF
    -0.59
     ASP
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.59
     citiz
    -0.59
    POSITIVE LOGITS
    furt
    0.91
    poll
    0.82
    wagen
    0.79
    stad
    0.79
    erella
    0.78
    adder
    0.77
    kamp
    0.73
    velt
    0.72
    rency
    0.69
     sidx
    0.69
    Activations Density 0.079%

    No Known Activations