© 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. 11-RES-JB
    11. 9332
    Prev
    Next
    INDEX
    Explanations

    Proper names or terms with unique spellings

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OD
    -0.93
     Nost
    -0.84
     Outs
    -0.83
     Abstract
    -0.82
     Bog
    -0.81
    ThumbnailImage
    -0.81
     Abbott
    -0.80
     Abram
    -0.77
     241
    -0.77
     AQ
    -0.76
    POSITIVE LOGITS
    le
    1.41
    les
    1.35
    el
    1.28
    leon
    1.26
    els
    1.24
    LE
    1.24
    elo
    1.19
    EL
    1.18
    LES
    1.17
    eli
    1.17
    Activations Density 0.274%

    No Known Activations