© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2435
    Prev
    Next
    INDEX
    Explanations

    information related to political elections and sporting events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LU
    -0.72
    linger
    -0.69
    REDACTED
    -0.68
    rang
    -0.67
    BILITIES
    -0.65
    ior
    -0.63
    awei
    -0.62
    ÑĮ
    -0.62
    ouf
    -0.61
    çīĪ
    -0.60
    POSITIVE LOGITS
     spite
    1.11
     favor
    1.04
     terms
    0.97
     favour
    0.95
     comparison
    0.88
     lieu
    0.87
    escap
    0.86
     vitro
    0.86
     succession
    0.86
     front
    0.84
    Activations Density 0.200%

    No Known Activations