© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating totality or completeness

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions that emphasize the concept of "all" 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
    enegger
    -0.74
     Challenges
    -0.74
     Rica
    -0.73
    ëĭ
    -0.67
    awaru
    -0.65
     Kahn
    -0.65
     Virtue
    -0.64
     meanwhile
    -0.63
     Janeiro
    -0.63
     Puzzles
    -0.61
    POSITIVE LOGITS
    usal
    0.86
    cast
    0.86
    alter
    0.82
    auc
    0.81
    usive
    0.80
    adic
    0.79
    ocratic
    0.75
    ab
    0.72
    -
    0.72
    burn
    0.71
    Activations Density 0.266%

    No Known Activations