© 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. 24037
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses containing a specific pattern or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms of concepts or changes

    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
    annis
    -0.60
    thodox
    -0.59
     Restaur
    -0.57
     DRAGON
    -0.57
     Doodle
    -0.57
     Bridges
    -0.53
    incial
    -0.53
    orsi
    -0.52
     beware
    -0.52
     weap
    -0.52
    POSITIVE LOGITS
    aldehyde
    1.23
    ative
    0.88
    ulating
    0.86
     of
    0.82
    atter
    0.79
    fitting
    0.75
    ulator
    0.75
    ãĥł
    0.73
    ular
    0.71
    ulated
    0.71
    Activations Density 0.017%

    No Known Activations