© 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. 14041
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "According" followed by information or attribution

    oai_token-act-pair · gpt-3.5-turbo

    statements that attribute information or claims to sources

    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
    DOWN
    -0.62
     godd
    -0.58
     heights
    -0.53
    âĻ¦
    -0.53
     eleph
    -0.53
     mathemat
    -0.53
     helicop
    -0.52
     swe
    -0.51
     gobl
    -0.50
     submar
    -0.50
    POSITIVE LOGITS
    ly
    1.14
     to
    0.95
    edly
    0.86
    liest
    0.82
    gest
    0.75
    lly
    0.74
    itionally
    0.68
    translation
    0.68
    LY
    0.67
    ities
    0.66
    Activations Density 0.035%

    No Known Activations