© 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. 0-RES-JB
    11. 19243
    Prev
    Next
    INDEX
    Explanations

    phone numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    open parentheses in text

    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
    staking
    -0.65
    esides
    -0.63
    iqueness
    -0.63
    ktop
    -0.62
    ¬¼
    -0.62
    adena
    -0.60
    %);
    -0.58
    wered
    -0.57
    successfully
    -0.56
    orthern
    -0.56
    POSITIVE LOGITS
     (
    2.02
     ("
    1.65
     ('
    1.59
     ([
    1.57
     (-
    1.56
     (~
    1.56
     (<
    1.55
     (.
    1.54
     (=
    1.48
     (>
    1.46
    Activations Density 0.178%

    No Known Activations