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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 8577
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal investigations and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incriminating evidence and notable individuals in a context of investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    MQ
    -0.80
    raise
    -0.70
    scill
    -0.69
     Goose
    -0.66
     Fighters
    -0.65
    EEK
    -0.65
     Scrib
    -0.63
     [|
    -0.63
    Ĥª
    -0.63
     Pelicans
    -0.61
    POSITIVE LOGITS
    inating
    0.99
     crater
    0.95
     incrim
    0.88
    inates
    0.83
    ifer
    0.78
    inated
    0.78
    ministic
    0.78
    ination
    0.77
    inate
    0.77
    inatory
    0.76
    Activations Density 0.028%

    No Known Activations