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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13273
    Prev
    Next
    INDEX
    Explanations

    terms related to proposed actions or policies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proposed" in the context of suggestions or recommendations

    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
     clicking
    -0.70
     msec
    -0.65
    vation
    -0.64
     Console
    -0.62
    nob
    -0.60
     bead
    -0.60
    fi
    -0.59
     knowing
    -0.59
     Reload
    -0.58
    ool
    -0.58
    POSITIVE LOGITS
     proposed
    3.47
     proposal
    2.06
     propose
    1.96
     proposals
    1.88
     proposes
    1.88
     proposing
    1.81
     suggested
    1.73
     contemplated
    1.65
     planned
    1.58
     hypothesized
    1.57
    Activations Density 0.014%

    No Known Activations