© 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. 10172
    Prev
    Next
    INDEX
    Explanations

    political affiliations and opinions

    oai_token-act-pair · gpt-3.5-turbo

    commas and punctuation marks

    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
    ¬¼
    -0.87
    ãĥ¯ãĥ³
    -0.78
    ²¾
    -0.75
    =-=-=-=-
    -0.70
    tnc
    -0.67
    ãĤ©
    -0.66
    atorium
    -0.65
    Ĥİ
    -0.65
    DragonMagazine
    -0.64
    gian
    -0.64
    POSITIVE LOGITS
     compared
    1.31
     whereas
    1.16
     versus
    1.10
     according
    1.06
     while
    0.97
     suggesting
    0.95
     indicating
    0.93
     contrasted
    0.90
     implying
    0.85
     respectively
    0.85
    Activations Density 0.154%

    No Known Activations