© 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. 8-RES-JB
    11. 18542
    Prev
    Next
    INDEX
    Explanations

    sentences signaling disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endeav
    -0.75
     instinct
    -0.69
     pill
    -0.69
     endeavour
    -0.68
     horrend
    -0.68
     charms
    -0.67
    arching
    -0.65
     compositions
    -0.65
    bred
    -0.65
    erning
    -0.65
    POSITIVE LOGITS
     Lastly
    1.27
     UNCLASSIFIED
    1.20
     Related
    1.20
     Finally
    1.16
     Meanwhile
    1.13
     Another
    1.11
     Additionally
    1.11
     Asked
    1.09
    <|endoftext|>
    1.08
     Notably
    1.06
    Activations Density 0.529%

    No Known Activations