© 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. 2763
    Prev
    Next
    INDEX
    Explanations

    phrases related to unintentional or accidental actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of accidental actions or events

    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
     Mov
    -0.68
    funding
    -0.68
     Amen
    -0.66
    åĮ
    -0.65
    Bridge
    -0.64
    åĬ
    -0.61
    Led
    -0.61
     Support
    -0.60
    Fit
    -0.60
     budgets
    -0.59
    POSITIVE LOGITS
     accidentally
    3.53
     inadvertently
    3.00
     unintentionally
    2.87
     unwittingly
    2.33
     mistakenly
    2.29
     accidental
    2.16
     inadvert
    2.15
     unintentional
    2.04
     unintended
    1.71
     incorrectly
    1.70
    Activations Density 0.031%

    No Known Activations