© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 24287
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication, particularly conversations with specific people or groups.

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" as well as a focus on interpersonal communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     additions
    -0.71
    ©¶æ¥µ
    -0.69
    irez
    -0.66
    ignty
    -0.66
    ģĸ
    -0.64
    ģ«
    -0.63
    adoes
    -0.62
     crops
    -0.60
    hover
    -0.60
    gradation
    -0.60
    POSITIVE LOGITS
     voic
    0.86
    plain
    0.76
     aloud
    0.72
     louder
    0.72
     TED
    0.72
     CNBC
    0.71
    aram
    0.71
    igraph
    0.67
     loudly
    0.67
    Spe
    0.65
    Activations Density 0.272%

    No Known Activations