© 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. 18449
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names containing the letter sequence 'q'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'q'

    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
     savior
    -0.65
     Oblivion
    -0.64
     chronological
    -0.64
     conduc
    -0.63
     Eclipse
    -0.62
     Lauder
    -0.61
     readable
    -0.61
    coni
    -0.60
     Savior
    -0.60
     Agric
    -0.60
    POSITIVE LOGITS
    aeda
    1.04
    iao
    1.02
    eus
    0.99
    iu
    0.98
    dn
    0.97
    een
    0.92
    eh
    0.90
    iang
    0.89
    rt
    0.89
    edo
    0.87
    Activations Density 0.027%

    No Known Activations