© 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. 0-RES-JB
    11. 6683
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vehicles or automotive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.87
    ecause
    -0.76
     ItemLevel
    -0.69
    ogun
    -0.67
    nian
    -0.64
    iard
    -0.62
    irlf
    -0.62
    agar
    -0.61
    olean
    -0.59
    ulner
    -0.58
    POSITIVE LOGITS
     antioxid
    0.88
    EStream
    0.86
    kefeller
    0.80
    Balt
    0.79
    ibaba
    0.72
     corrid
    0.69
    natureconservancy
    0.69
    ĵĺ
    0.68
     Seym
    0.67
    ĸļ
    0.66
    Activations Density 14.904%

    No Known Activations