Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4117
    Prev
    Next
    INDEX
    Explanations

    issues, criticisms, and objections

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.76
    ggles
    -0.70
     skyrocket
    -0.66
    ctica
    -0.63
    aults
    -0.61
    byter
    -0.61
    chet
    -0.60
    clerosis
    -0.59
    umatic
    -0.59
    rencies
    -0.58
    POSITIVE LOGITS
     whatsoever
    0.76
     attaching
    0.74
    Nusra
    0.66
     letting
    0.65
     admitting
    0.65
    lihood
    0.63
     having
    0.61
     saying
    0.61
    doing
    0.61
    acity
    0.60
    Activations Density 0.122%

    No Known Activations