© 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. 4-RES-JB
    11. 14896
    Prev
    Next
    INDEX
    Explanations

    the word "convenient" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    references to convenience in various contexts

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

    No Comments

    Negative Logits
    authorized
    -0.77
    Song
    -0.75
    ciplinary
    -0.73
    essee
    -0.73
    song
    -0.72
    grave
    -0.70
    brance
    -0.70
    fighters
    -0.70
    hun
    -0.69
    dust
    -0.67
    POSITIVE LOGITS
     convenient
    1.10
     excuse
    0.94
     shortcuts
    0.91
    ãĥ¼ãĥĨ
    0.90
     conveniently
    0.87
     conven
    0.86
     convenience
    0.82
    venient
    0.78
     scapego
    0.78
     excuses
    0.76
    Activations Density 0.015%

    No Known Activations