© 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. 2-RES-JB
    11. 9458
    Prev
    Next
    INDEX
    Explanations

    terms related to preparation or early planning in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to upfront costs or preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifling
    -0.66
    nesota
    -0.65
     Maw
    -0.64
    ĸļ
    -0.63
     Jarvis
    -0.63
    whe
    -0.63
     Wend
    -0.63
    entry
    -0.61
    Grand
    -0.60
     Glover
    -0.59
    POSITIVE LOGITS
     upfront
    1.22
    alone
    0.77
    leneck
    0.73
    ledged
    0.72
     hurdle
    0.72
    comings
    0.71
     rehears
    0.69
    intensive
    0.69
    lied
    0.68
     onstage
    0.68
    Activations Density 0.009%

    No Known Activations