© 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. 9054
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a high degree or level of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to varying degrees of importance or impact

    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
    ocene
    -0.72
    ovie
    -0.68
    dor
    -0.68
    ulhu
    -0.66
     whence
    -0.65
    hyde
    -0.65
    naire
    -0.65
     Register
    -0.65
    washer
    -0.64
    ften
    -0.64
    POSITIVE LOGITS
     amounts
    1.22
     doses
    1.04
     quantities
    1.00
     levels
    0.97
     significance
    0.89
     technical
    0.87
     modifications
    0.86
     proportions
    0.85
     kinds
    0.83
     periods
    0.83
    Activations Density 0.550%

    No Known Activations