© 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. 10155
    Prev
    Next
    INDEX
    Explanations

    references to the IRS (Internal Revenue Service) in text

    oai_token-act-pair · gpt-3.5-turbo

    references to the IRS

    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
    boards
    -0.86
    hots
    -0.82
    izations
    -0.80
    ifest
    -0.77
    axter
    -0.76
    isations
    -0.73
    ties
    -0.71
    theless
    -0.70
     Kard
    -0.68
    board
    -0.67
    POSITIVE LOGITS
     IRS
    0.99
     bureaucracy
    0.79
    RECT
    0.76
     levied
    0.76
     sting
    0.75
     scrutiny
    0.74
     stalking
    0.74
    eteria
    0.74
     Revenue
    0.73
     whistleblower
    0.73
    Activations Density 0.018%

    No Known Activations