© 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. 18727
    Prev
    Next
    INDEX
    Explanations

    mentions of the fictional character "Spider-Man"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of "Sp," which likely stands for a specific term or entity mentioned frequently in the document

    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
    ãĥĥãĥĪ
    -0.71
    İĭ
    -0.68
     separatist
    -0.67
    eering
    -0.60
    ĪĴ
    -0.60
     defaults
    -0.60
     Incarnation
    -0.59
    furt
    -0.58
     fringe
    -0.58
    WAYS
    -0.57
    POSITIVE LOGITS
    atial
    1.40
    aghetti
    1.28
    ooky
    1.26
    ruce
    1.21
    okes
    1.18
    rawl
    1.18
    indle
    1.15
    itt
    1.13
    itting
    1.13
    encer
    1.11
    Activations Density 0.027%

    No Known Activations