© 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. 0-RES-JB
    11. 2814
    Prev
    Next
    INDEX
    Explanations

    words related to signing or re-signing agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sign" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     treated
    -0.73
     bent
    -0.67
    elf
    -0.63
     paralysis
    -0.61
     adventure
    -0.61
     dungeon
    -0.61
     Hemp
    -0.59
     monopoly
    -0.59
     tumble
    -0.59
     nylon
    -0.59
    POSITIVE LOGITS
    sign
    4.29
    Sign
    2.22
    signed
    2.15
     Sign
    2.10
     sign
    1.81
    SIGN
    1.65
     Signs
    1.61
     SIGN
    1.61
     signing
    1.44
     signs
    1.40
    Activations Density 0.011%

    No Known Activations