© 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. 21244
    Prev
    Next
    INDEX
    Explanations

    lists of numbers expressed through text

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

    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
    ãĤ´ãĥ³
    -0.76
    ighed
    -0.70
    è£ħ
    -0.70
    ļéĨĴ
    -0.68
    pec
    -0.67
    vale
    -0.67
    prise
    -0.66
    SourceFile
    -0.64
    apolis
    -0.64
    hig
    -0.63
    POSITIVE LOGITS
     nobody
    1.11
     they
    1.04
     there
    0.99
    they
    0.95
     somew
    0.93
     we
    0.92
     everybody
    0.90
    there
    0.89
     it
    0.89
     yeah
    0.85
    Activations Density 0.300%

    No Known Activations