© 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. 9-RES-JB
    11. 13083
    Prev
    Next
    INDEX
    Explanations

    accusations or accusations of wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accused" associated with various allegations and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.78
    opter
    -0.74
    awk
    -0.73
    ARCH
    -0.72
    patch
    -0.67
    OPLE
    -0.66
    ental
    -0.65
    awks
    -0.64
    Exit
    -0.64
    irds
    -0.63
    POSITIVE LOGITS
     of
    0.80
     unfairly
    0.79
     wrongly
    0.76
     falsely
    0.75
    ilities
    0.74
     alleging
    0.73
     accusing
    0.72
     rapist
    0.72
    onia
    0.71
     leve
    0.71
    Activations Density 0.036%

    No Known Activations