© 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. 7-RES-JB
    11. 13484
    Prev
    Next
    INDEX
    Explanations

    words related to night time activities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "night" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eries
    -0.64
    åĬ
    -0.63
     Bucc
    -0.62
     PROC
    -0.61
     conson
    -0.60
     Cosponsors
    -0.60
     LINE
    -0.60
    LP
    -0.59
    oute
    -0.59
    SHIP
    -0.58
    POSITIVE LOGITS
    fall
    0.92
    noon
    0.91
    aturdays
    0.85
    worms
    0.71
    hedon
    0.67
    falls
    0.67
     waking
    0.67
    hover
    0.66
    jet
    0.66
    wagen
    0.65
    Activations Density 0.084%

    No Known Activations