© 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. 14772
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information included within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in the text

    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
     appropri
    -0.76
     obscurity
    -0.76
     inund
    -0.75
     veget
    -0.75
     antiv
    -0.72
     overfl
    -0.71
     undet
    -0.71
     microbiome
    -0.71
     diving
    -0.70
     nutrient
    -0.70
    POSITIVE LOGITS
    âĢ¦)
    1.35
    emphasis
    1.28
    laughs
    1.14
    ...)
    1.14
    sic
    1.08
    hide
    1.07
    See
    1.05
    CBC
    1.05
    Laughs
    1.03
    Unless
    0.99
    Activations Density 0.062%

    No Known Activations