© 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. 6-RES-JB
    11. 11617
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a contrast or a state of being

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sometime
    -0.63
     Opportun
    -0.63
     Introdu
    -0.60
     rethink
    -0.58
     Reduce
    -0.58
     Lack
    -0.57
    uctions
    -0.57
    itton
    -0.57
     Wrap
    -0.57
    gal
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.08
     ever
    1.01
     anymore
    1.00
     necessarily
    0.98
     nor
    0.97
     EVER
    0.91
     remotely
    0.84
     anywhere
    0.83
     presently
    0.79
     bothered
    0.78
    Activations Density 0.104%

    No Known Activations