© 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. 3-RES-JB
    11. 15197
    Prev
    Next
    INDEX
    Explanations

    words related to narration or storytelling

    oai_token-act-pair · gpt-3.5-turbo

    narrative-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ful
    -0.70
    peak
    -0.68
    anwhile
    -0.66
    xual
    -0.65
    cules
    -0.62
    theless
    -0.62
     corpus
    -0.62
    fully
    -0.61
    flake
    -0.61
     EFF
    -0.61
    POSITIVE LOGITS
    ative
    1.14
    atives
    1.06
    amus
    0.93
    acan
    0.91
    ator
    0.89
    agan
    0.89
    abee
    0.88
    abo
    0.87
    ationally
    0.86
    agement
    0.85
    Activations Density 0.018%

    No Known Activations