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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 23994
    Prev
    Next
    INDEX
    Explanations

    phrases indicating what to expect or look for in a given context

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to anticipation or expectations

    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
    trak
    -0.68
    mone
    -0.65
     inactive
    -0.63
     moot
    -0.62
     Fever
    -0.62
     DOT
    -0.61
    jury
    -0.60
    rid
    -0.59
    tur
    -0.56
    imilar
    -0.56
    POSITIVE LOGITS
    ãĤ´
    0.80
    ACA
    0.76
     beforehand
    0.73
    ETS
    0.72
     versus
    0.72
     entails
    0.72
    ?:
    0.71
    çIJ
    0.71
     depends
    0.68
    ?,
    0.67
    Activations Density 0.255%

    No Known Activations