© 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. 0-RES-JB
    11. 19990
    Prev
    Next
    INDEX
    Explanations

    instances of the word "chan" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the online community 4chan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ref
    -0.64
     cellar
    -0.64
     enterprise
    -0.63
     independents
    -0.63
     formulas
    -0.63
     Independence
    -0.62
     prem
    -0.62
     reliance
    -0.61
     IR
    -0.61
     indictment
    -0.61
    POSITIVE LOGITS
    chan
    4.94
    Chan
    2.48
    chat
    1.46
    sama
    1.44
    kun
    1.43
    san
    1.32
    chant
    1.26
    ch
    1.20
    chin
    1.20
    cham
    1.13
    Activations Density 0.010%

    No Known Activations