Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18901
    Prev
    Next
    INDEX
    Explanations

    websites or links

    oai_token-act-pair · gpt-3.5-turbo

    references to URLs or web 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
     oral
    -0.74
     Scouting
    -0.72
     brackets
    -0.70
     graffiti
    -0.70
     intercept
    -0.69
     whims
    -0.69
     voting
    -0.68
     sneak
    -0.66
     expansion
    -0.64
     summ
    -0.64
    POSITIVE LOGITS
    edu
    1.82
    org
    1.66
    gov
    1.48
    nih
    1.47
    nl
    1.43
    jp
    1.43
    kr
    1.37
    com
    1.36
    net
    1.36
    uni
    1.29
    Activations Density 0.039%

    No Known Activations