© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 4171
    Prev
    Next
    INDEX
    Explanations

    names or terms related to financial or technical matters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media and informants

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

    No Comments

    Negative Logits
     Tycoon
    -0.84
    usk
    -0.82
    pled
    -0.77
    pse
    -0.76
    ples
    -0.75
    bish
    -0.73
    ttle
    -0.73
    bon
    -0.72
    pling
    -0.71
    gypt
    -0.70
    POSITIVE LOGITS
    ational
    0.76
    schild
    0.75
    Sharp
    0.73
     Vega
    0.72
    ontent
    0.72
    iture
    0.71
    å°Ĩ
    0.70
    Past
    0.67
    OTE
    0.66
    ienne
    0.65
    Activations Density 0.030%

    No Known Activations