© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9929
    Prev
    Next
    INDEX
    Explanations

    statements indicating knowledge or awareness of a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge and awareness in various contexts

    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
     suggestion
    -0.77
     reluct
    -0.71
    wik
    -0.69
    edia
    -0.66
     insistence
    -0.65
     understandably
    -0.64
     recommends
    -0.64
    ioch
    -0.63
    ertodd
    -0.63
     Feast
    -0.62
    POSITIVE LOGITS
     outnumbered
    0.77
     wasting
    0.75
     tread
    0.72
     kindred
    0.72
     belong
    0.71
     invincible
    0.71
     done
    0.68
    done
    0.67
     owed
    0.67
     witnessing
    0.65
    Activations Density 0.301%

    No Known Activations