© 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. 9-RES-JB
    11. 6853
    Prev
    Next
    INDEX
    Explanations

    timestamps indicating a point in time in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favour
    -0.73
    adr
    -0.69
    tnc
    -0.67
    #$
    -0.67
    rouse
    -0.63
     favor
    -0.62
    natureconservancy
    -0.61
    uras
    -0.61
    vt
    -0.61
    ËĪ
    -0.61
    POSITIVE LOGITS
     versions
    0.85
    noon
    0.85
     editions
    0.84
     revelations
    0.79
    etheless
    0.76
     indications
    0.75
     analyses
    0.72
     Accounts
    0.72
     translations
    0.71
     Stories
    0.70
    Activations Density 0.046%

    No Known Activations