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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3-RES-JB
    6. 10968
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ologically
    -0.67
    ULE
    -0.67
    respective
    -0.67
    arily
    -0.67
    Magikarp
    -0.66
    aciously
    -0.66
    ple
    -0.66
    itia
    -0.65
    cer
    -0.65
    ename
    -0.65
    POSITIVE LOGITS
     Baldwin
    1.24
     Osw
    0.87
    reath
    0.76
    ©¶æ¥µ
    0.76
    mpeg
    0.75
    halla
    0.75
    rites
    0.71
    urst
    0.70
     flats
    0.68
    racuse
    0.68
    Activations Density 0.015%

    No Known Activations