© 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. 0-RES-JB
    11. 2916
    Prev
    Next
    INDEX
    Explanations

    terms related to prominent figures or places

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prominence and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CAP
    -0.74
     owl
    -0.68
     Zimmer
    -0.66
     SY
    -0.65
    igious
    -0.65
     membr
    -0.64
     Lump
    -0.64
     PAT
    -0.63
     Wiley
    -0.60
     Pyth
    -0.59
    POSITIVE LOGITS
    inent
    4.11
    inence
    1.67
    inently
    1.45
    enthal
    1.31
    ERN
    1.07
    urbed
    1.04
    issions
    0.99
    umar
    0.97
    origin
    0.91
    vre
    0.90
    Activations Density 0.029%

    No Known Activations