© 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. 8621
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or searching for something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "find" in various contexts

    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
    perty
    -0.71
    puff
    -0.68
    icago
    -0.68
    dating
    -0.65
    adding
    -0.64
    itent
    -0.64
    psey
    -0.64
     paced
    -0.64
     fracturing
    -0.63
     concess
    -0.63
    POSITIVE LOGITS
    ById
    0.87
    Ô
    0.84
    omething
    0.77
    使
    0.77
    ãĤ¼
    0.76
     loopholes
    0.76
    uments
    0.74
     out
    0.70
    ãĤ¦
    0.69
    ource
    0.67
    Activations Density 0.057%

    No Known Activations