© 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. 10-RES-JB
    11. 12152
    Prev
    Next
    INDEX
    Explanations

    descriptions related to human facial features

    oai_token-act-pair · gpt-3.5-turbo

    references to faces and facial features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.75
    æ©Ł
    -0.71
    selves
    -0.71
    YA
    -0.65
    isexual
    -0.65
    Leaks
    -0.64
    CAST
    -0.64
    iscopal
    -0.64
    ondo
    -0.63
     mosqu
    -0.63
    POSITIVE LOGITS
    plate
    1.19
    plant
    1.00
    plates
    0.97
     mask
    0.93
     masks
    0.91
    offs
    0.90
    BOOK
    0.89
     emoji
    0.88
     veil
    0.88
    beard
    0.84
    Activations Density 0.036%

    No Known Activations