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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6371
    Prev
    Next
    INDEX
    Explanations

    text containing a specific sequence of characters 'isin'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itably
    -0.78
    schild
    -0.73
    eus
    -0.73
    inately
    -0.70
    ries
    -0.67
    heastern
    -0.66
    rified
    -0.65
     populated
    -0.64
     Fired
    -0.64
    izoph
    -0.64
    POSITIVE LOGITS
    uten
    0.84
    urations
    0.81
     inhibitors
    0.76
    doi
    0.72
    ÏĦ
    0.72
    utics
    0.72
    atory
    0.71
    manship
    0.71
    atform
    0.70
    '"
    0.67
    Activations Density 0.019%

    No Known Activations