© 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. 16463
    Prev
    Next
    INDEX
    Explanations

    specific number sequences

    oai_token-act-pair · gpt-3.5-turbo
    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
    rieg
    -0.76
     brim
    -0.76
    ongs
    -0.70
    76561
    -0.69
    quit
    -0.68
    mx
    -0.67
    atana
    -0.65
    blogs
    -0.65
    lyss
    -0.64
     fing
    -0.63
    POSITIVE LOGITS
    incial
    0.66
    crow
    0.63
    itto
    0.63
     Krish
    0.62
     Irving
    0.61
     Autism
    0.60
    ersen
    0.60
     Aren
    0.58
     deficits
    0.58
     vaccine
    0.57
    Activations Density 0.000%

    No Known Activations