© 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. 21485
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a particularly emphasized and impactful statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or reactions

    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
    ixt
    -0.79
    elaide
    -0.78
    »Ĵ
    -0.75
    usalem
    -0.73
    abilia
    -0.70
    emporary
    -0.70
    uese
    -0.69
    ascript
    -0.68
    yles
    -0.67
    estern
    -0.66
    POSITIVE LOGITS
     Its
    1.46
    Its
    1.28
     Their
    1.15
     its
    1.12
     ITS
    1.05
     They
    1.04
    Their
    1.01
    their
    0.98
    They
    0.96
    they
    0.96
    Activations Density 0.622%

    No Known Activations