© 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. 7-RES-JB
    11. 18775
    Prev
    Next
    INDEX
    Explanations

    phrases expressing approval or agreement

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods and closing punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jah
    -0.79
    ilion
    -0.71
    community
    -0.70
    ral
    -0.70
    ãĥIJ
    -0.66
    reb
    -0.66
    blers
    -0.65
    med
    -0.65
    reens
    -0.63
    pen
    -0.62
    POSITIVE LOGITS
     Anyway
    0.92
     srfAttach
    0.84
     Likewise
    0.74
    uits
    0.73
     Instead
    0.73
     Similarly
    0.72
    */
    0.72
     Modes
    0.72
     Accordingly
    0.71
     Eventually
    0.70
    Activations Density 0.051%

    No Known Activations