© 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. 2-RES-JB
    11. 8927
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts or efforts that do not succeed

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to situations that yield no results or are unfruitful

    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
    eric
    -0.81
     Grove
    -0.73
    mac
    -0.70
     Nose
    -0.67
    protein
    -0.66
    Mac
    -0.63
     Patriarch
    -0.63
     Dough
    -0.61
     coron
    -0.61
    irrel
    -0.60
    POSITIVE LOGITS
     avail
    1.28
    abilities
    1.05
    ĸļ
    0.98
     mathemat
    0.97
    ibility
    0.91
    urations
    0.86
    ible
    0.83
    ãģĨ
    0.83
    ilege
    0.82
    querade
    0.81
    Activations Density 0.009%

    No Known Activations