© 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. 11-RES-JB
    11. 2620
    Prev
    Next
    INDEX
    Explanations

    short messages or phrases meant to convey emotion or advice

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation and sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distinguished
    -0.66
     identified
    -0.62
     Rodham
    -0.61
     Quarterly
    -0.60
     explor
    -0.59
     staggered
    -0.59
     McH
    -0.59
     Quart
    -0.59
     Greenberg
    -0.59
     calibrated
    -0.59
    POSITIVE LOGITS
    BUT
    1.44
    why
    1.33
    please
    1.32
    Anyway
    1.32
    thank
    1.27
    Therefore
    1.26
    lol
    1.25
    sorry
    1.23
    Secondly
    1.21
    so
    1.19
    Activations Density 0.581%

    No Known Activations