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. 7-RES-JB
    6. 6087
    Prev
    Next
    INDEX
    Explanations

    numbers followed by the word "million" in documents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outstanding" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -0.91
    udic
    -0.84
    olog
    -0.83
    ©¶æ
    -0.82
    jah
    -0.81
    walk
    -0.79
    oleon
    -0.79
    opt
    -0.78
    borg
    -0.78
    uton
    -0.76
    POSITIVE LOGITS
     outstanding
    0.92
    ances
    0.90
     debts
    0.80
    NESS
    0.80
     warrants
    0.79
     balances
    0.74
     PAN
    0.73
     delinquent
    0.73
     debt
    0.72
     contribution
    0.71
    Activations Density 0.049%

    No Known Activations