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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 22291
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to strong attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ten" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jerk
    -0.66
     Indust
    -0.65
     DRAG
    -0.62
    ****************
    -0.60
    TextColor
    -0.59
    LEASE
    -0.58
    unct
    -0.57
    LCS
    -0.57
     Tonight
    -0.56
    HY
    -0.56
    POSITIVE LOGITS
    acity
    1.37
    aciously
    1.36
    acious
    1.34
    ured
    1.23
    uous
    1.20
    uously
    1.08
     thousand
    1.07
    fold
    1.06
    ements
    1.04
    zin
    0.96
    Activations Density 0.038%

    No Known Activations