© 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. 8-RES-JB
    11. 4046
    Prev
    Next
    INDEX
    Explanations

    phrases related to pipes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pipe" and related terms

    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
    enance
    -0.87
    INAL
    -0.74
    ãħĭ
    -0.68
     Redemption
    -0.67
    istical
    -0.64
    istic
    -0.62
    dale
    -0.60
    grounds
    -0.60
    istically
    -0.59
    ization
    -0.58
    POSITIVE LOGITS
    acity
    0.75
    prus
    0.74
    join
    0.73
    ascus
    0.73
    qi
    0.73
    aukee
    0.73
    teen
    0.73
    fen
    0.72
    kered
    0.72
    etr
    0.72
    Activations Density 0.079%

    No Known Activations