© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a time indication like "m" for minutes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'm' in the text

    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
     Accountability
    -0.63
     referen
    -0.62
    FontSize
    -0.60
     fringe
    -0.59
     lasting
    -0.57
     questioning
    -0.57
     broth
    -0.57
     compliments
    -0.56
    chnology
    -0.56
     pineapple
    -0.55
    POSITIVE LOGITS
    m
    3.55
    mn
    1.80
    mology
    1.78
    mi
    1.70
    ms
    1.68
    mos
    1.65
    mic
    1.64
    mu
    1.63
    mol
    1.60
    met
    1.57
    Activations Density 0.074%

    No Known Activations