© 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. 7-RES-JB
    11. 21285
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly related to popular culture, technology, and media

    oai_token-act-pair · gpt-3.5-turbo

    titles and names of notable films and television shows

    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
    etheless
    -0.75
    ometimes
    -0.63
    ength
    -0.58
    upon
    -0.57
    surprisingly
    -0.54
    fitted
    -0.53
    repre
    -0.52
    uitive
    -0.51
     destro
    -0.51
     withd
    -0.49
    POSITIVE LOGITS
    ")
    1.70
    ").
    1.58
    "),
    1.57
    "]
    1.55
    ",
    1.53
    "—
    1.51
    "?
    1.48
    "
    1.43
    .")
    1.41
    ".
    1.37
    Activations Density 0.532%

    No Known Activations