© 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. 8-RES-JB
    11. 9886
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by descriptions or specifications of objects

    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
    projects
    -0.81
    Companies
    -0.73
    event
    -0.71
    HAEL
    -0.71
    reports
    -0.70
    dogs
    -0.70
    cakes
    -0.70
    ateurs
    -0.70
    bis
    -0.69
    books
    -0.68
    POSITIVE LOGITS
     tendency
    1.23
     resemblance
    1.14
     similarity
    1.03
     lifespan
    1.00
     distinctive
    0.97
     propensity
    0.94
     similarities
    0.94
     resonance
    0.93
     knack
    0.93
     penchant
    0.92
    Activations Density 0.287%

    No Known Activations