© 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. 9-RES-JB
    11. 14845
    Prev
    Next
    INDEX
    Explanations

    time-related words and phrases expressing short durations

    oai_token-act-pair · gpt-3.5-turbo

    time-related phrases and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anium
    -0.71
    cause
    -0.64
    icket
    -0.64
    because
    -0.63
    ums
    -0.61
    udeb
    -0.61
    ogly
    -0.59
     shortest
    -0.59
    ================================================================
    -0.58
    inki
    -0.58
    POSITIVE LOGITS
     they
    0.88
     we
    0.85
     thereafter
    0.78
     there
    0.78
     he
    0.76
    ,
    0.75
    ,.
    0.73
     however
    0.71
     she
    0.71
    adays
    0.66
    Activations Density 0.378%

    No Known Activations