© 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. 4-RES-JB
    11. 505
    Prev
    Next
    INDEX
    Explanations

    references to government or authority figures, particularly those related to oversight and investigations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "inspector."

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

    No Comments

    Negative Logits
    theless
    -1.01
    birth
    -0.79
    eda
    -0.70
    erry
    -0.70
    talk
    -0.69
    words
    -0.68
    asted
    -0.65
    eton
    -0.64
    demand
    -0.64
    esville
    -0.63
    POSITIVE LOGITS
     Gadget
    1.09
    atis
    0.85
    Reviewer
    0.85
     Inspector
    0.83
     Spac
    0.82
     inspector
    0.82
    itle
    0.76
    orate
    0.76
    atus
    0.73
    ror
    0.72
    Activations Density 0.011%

    No Known Activations