© 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. 2-RES-JB
    11. 17037
    Prev
    Next
    INDEX
    Explanations

    words related to body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to physical appearances, particularly focused on body parts and health-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.70
     FISA
    -0.65
    nown
    -0.65
     Archangel
    -0.64
     DRAG
    -0.64
     Pilgrim
    -0.64
    quartered
    -0.63
     Defenders
    -0.63
    inement
    -0.63
     Witness
    -0.63
    POSITIVE LOGITS
    ours
    0.92
    pton
    0.92
    geries
    0.87
    ahon
    0.86
    gery
    0.82
    mat
    0.81
    arter
    0.79
     tum
    0.79
    sheets
    0.78
    tub
    0.77
    Activations Density 0.019%

    No Known Activations