© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 9517
    Prev
    Next
    INDEX
    Explanations

    mentions of legal documents being signed into law

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "signed," indicating legislative or formal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Layer
    -0.71
    ETHOD
    -0.70
     nerv
    -0.70
    @#&
    -0.68
    adish
    -0.66
    Zone
    -0.64
    Middle
    -0.64
     Islands
    -0.63
    rough
    -0.62
    series
    -0.61
    POSITIVE LOGITS
    atories
    1.11
     signed
    0.89
    chant
    0.88
    */(
    0.87
     petitions
    0.84
     signing
    0.83
    sign
    0.82
     sign
    0.79
    ature
    0.78
     Signed
    0.78
    Activations Density 0.026%

    No Known Activations