© 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. 19427
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying the intensity of a concept or action

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating a lack of significant impact or importance

    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
    ividual
    -0.86
    spin
    -0.70
    ulative
    -0.67
    lace
    -0.67
    CU
    -0.66
    eki
    -0.66
    alez
    -0.66
    MAT
    -0.65
    hang
    -0.65
    swick
    -0.65
    POSITIVE LOGITS
     percept
    0.82
     distinguish
    0.79
     paralle
    0.74
    Ń·
    0.73
     dime
    0.72
    ł
    0.71
    icable
    0.71
     incons
    0.70
     insignificant
    0.70
    withstanding
    0.70
    Activations Density 0.010%

    No Known Activations