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

    Neuronpedia

    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. 10-RES-JB
    11. 13641
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions being done

    oai_token-act-pair · gpt-3.5-turbo

    repetitive usages of the verb forms "do" and "did" in relation to actions performed

    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
    furt
    -0.68
    Board
    -0.64
    CLUD
    -0.61
     Entered
    -0.59
    inently
    -0.59
    ricted
    -0.58
    ussen
    -0.57
     Det
    -0.56
    hner
    -0.56
    RAFT
    -0.55
    POSITIVE LOGITS
    pez
    1.15
     differently
    1.02
     wrong
    0.94
     administr
    0.91
    wrong
    0.81
    actic
    0.76
     succeed
    0.73
    Äĩ
    0.73
    hing
    0.72
    onga
    0.72
    Activations Density 0.061%

    No Known Activations