© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2212
    Prev
    Next
    INDEX
    Explanations

    the word "Even" followed by information or a contrast

    oai_token-act-pair · gpt-3.5-turbo

    the word "Even" as a significant marker in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rend
    -0.90
    aim
    -0.87
    ãĤ´ãĥ³
    -0.73
    FG
    -0.71
    ilver
    -0.70
    urn
    -0.68
    vich
    -0.68
    chnology
    -0.67
    rib
    -0.67
    cember
    -0.67
    POSITIVE LOGITS
     though
    1.20
     worse
    0.98
     tho
    0.95
     if
    0.84
     paran
    0.81
     seasoned
    0.81
     stranger
    0.73
    handed
    0.71
     assuming
    0.71
    song
    0.69
    Activations Density 0.042%

    No Known Activations