© 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. 1-RES-JB
    11. 2744
    Prev
    Next
    INDEX
    Explanations

    dates or durations

    oai_token-act-pair · gpt-3.5-turbo

    the word "Until" with varying levels of emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roph
    -0.68
    spir
    -0.66
    eny
    -0.66
    hazard
    -0.66
    aird
    -0.64
    tre
    -0.64
    cap
    -0.64
    qua
    -0.64
    hack
    -0.63
    alian
    -0.63
    POSITIVE LOGITS
    soever
    1.01
     Until
    0.92
    Until
    0.84
    ĸļ
    0.77
    MENTS
    0.76
    thood
    0.75
     Till
    0.73
     Til
    0.73
    onda
    0.71
    terday
    0.70
    Activations Density 0.009%

    No Known Activations