© 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. 10-RES-JB
    11. 20478
    Prev
    Next
    INDEX
    Explanations

    instances of accusations or allegations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accused" associated with various subjects

    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
    ahime
    -0.72
    GROUP
    -0.68
    ratulations
    -0.66
    EMS
    -0.66
    awk
    -0.63
    Exit
    -0.61
    NOR
    -0.61
    irds
    -0.59
    rats
    -0.59
    OPLE
    -0.58
    POSITIVE LOGITS
     of
    0.92
     falsely
    0.80
     unfairly
    0.78
     by
    0.77
     wrongly
    0.76
    onia
    0.72
     wrongdoing
    0.69
     cheating
    0.69
     thereof
    0.69
     repeatedly
    0.69
    Activations Density 0.038%

    No Known Activations