© 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. 10033
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a particular punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey strong emotional reactions or states

    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
     carbohyd
    -0.93
     concess
    -0.90
     volunte
    -0.88
     teasp
    -0.87
     rall
    -0.83
    ¥ŀ
    -0.83
     subur
    -0.83
     pione
    -0.82
     nomine
    -0.81
     challeng
    -0.81
    POSITIVE LOGITS
     Especially
    1.74
     Firstly
    1.47
     Normally
    1.41
     Certainly
    1.39
     Surely
    1.39
     Particularly
    1.35
     Wouldn
    1.35
     Maybe
    1.33
     Honestly
    1.31
    Especially
    1.28
    Activations Density 0.357%

    No Known Activations