© 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. 1-RES-JB
    11. 9427
    Prev
    Next
    INDEX
    Explanations

    verbs starting with "mis-" that indicate incorrect or improper behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "mis," indicating mistakes or mismanagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetti
    -0.77
     Enhancement
    -0.74
    ¯¯¯¯
    -0.72
    INGS
    -0.66
     Bron
    -0.66
    uesday
    -0.65
     Norn
    -0.64
    inction
    -0.63
    itutional
    -0.63
    auri
    -0.63
    POSITIVE LOGITS
    appropri
    1.04
     mis
    0.95
    cellaneous
    0.88
    pell
    0.88
    informed
    0.84
    iscal
    0.83
    aligned
    0.82
    pelled
    0.81
    beh
    0.81
    mist
    0.80
    Activations Density 0.008%

    No Known Activations