© 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. 9061
    Prev
    Next
    INDEX
    Explanations

    phrases that are used to introduce or emphasize information in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as" used to introduce comparisons or clarifications

    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
    zona
    -0.76
    stals
    -0.72
    èĪ
    -0.69
    oral
    -0.67
    vier
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    cean
    -0.65
    ASED
    -0.65
    opian
    -0.65
    eating
    -0.65
    POSITIVE LOGITS
     usual
    1.31
     always
    1.10
     mentioned
    0.97
     evidenced
    0.97
     noted
    0.90
     aforementioned
    0.87
     ever
    0.85
     stated
    0.85
     far
    0.85
     expected
    0.84
    Activations Density 0.089%

    No Known Activations