© 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. 17313
    Prev
    Next
    INDEX
    Explanations

    website URLs and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    websites and email addresses

    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
     Grill
    -0.95
     Colossus
    -0.95
     Maher
    -0.95
     Morse
    -0.93
     Clause
    -0.92
     Jonah
    -0.87
     Hardy
    -0.87
     Sunni
    -0.86
     Maul
    -0.85
     Moody
    -0.85
    POSITIVE LOGITS
    saf
    1.58
    facebook
    1.54
    united
    1.49
    aqu
    1.48
    cit
    1.46
    sand
    1.46
    christ
    1.44
    bitcoin
    1.42
    college
    1.42
    soc
    1.41
    Activations Density 0.140%

    No Known Activations