© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14852
    Prev
    Next
    INDEX
    Explanations

    references to the online platform "Vulture" with decreasing activation values indicating lesser matches

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "culture" and its variations

    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
    coming
    -0.71
    boa
    -0.70
    minster
    -0.69
    lished
    -0.69
    soDeliveryDate
    -0.68
    uki
    -0.67
    abet
    -0.65
    uffer
    -0.64
    lock
    -0.64
    ilts
    -0.64
    POSITIVE LOGITS
    ulture
    1.03
    cules
    0.87
     Culture
    0.76
     Appropri
    0.75
    llo
    0.73
    ultural
    0.73
    urally
    0.73
    llor
    0.71
     srfAttach
    0.70
     Clicker
    0.69
    Activations Density 0.019%

    No Known Activations