© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    words related to contorting or writhing movements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wr" or variations of it, indicating distress or struggle

    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
    RON
    -0.84
    BALL
    -0.73
    ãĥ´
    -0.68
     Defenders
    -0.67
    ctica
    -0.66
    croft
    -0.65
    anamo
    -0.63
    姫
    -0.62
    cair
    -0.62
    ablishment
    -0.61
    POSITIVE LOGITS
    inkle
    1.34
    angler
    1.18
    inging
    1.15
    angling
    1.12
    ights
    1.06
    angle
    1.03
    ings
    0.98
    angled
    0.97
    iggle
    0.97
    angles
    0.95
    Activations Density 0.007%

    No Known Activations