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. 4-RES-JB
    6. 23938
    Prev
    Next
    INDEX
    Explanations

    words related to logic and reason

    oai_token-act-pair · gpt-3.5-turbo

    references to rationality

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

    No Comments

    Negative Logits
    RAW
    -0.79
    ammy
    -0.78
    rael
    -0.74
    luster
    -0.73
    chin
    -0.73
    hold
    -0.71
    kick
    -0.69
    HI
    -0.68
     Nou
    -0.68
    IG
    -0.68
    POSITIVE LOGITS
    izations
    1.08
    ization
    0.99
    isations
    0.98
    izes
    0.95
    tarian
    0.95
    iation
    0.94
    istic
    0.94
    izing
    0.91
    iated
    0.86
    ized
    0.86
    Activations Density 0.005%

    No Known Activations