© 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. 14866
    Prev
    Next
    INDEX
    Explanations

    words related to proportionality and disproportionality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to proportionality and disparity

    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
    arro
    -0.85
    aneers
    -0.81
    rums
    -0.78
    scape
    -0.78
    ouri
    -0.77
    ologies
    -0.77
    Ö¼
    -0.75
    izen
    -0.74
    ingers
    -0.73
    strom
    -0.72
    POSITIVE LOGITS
     proportional
    1.06
     representation
    0.78
     arithmetic
    0.77
     equally
    0.75
     electoral
    0.71
     proportion
    0.71
     incorporation
    0.70
     illegitimate
    0.69
    isable
    0.68
     successor
    0.68
    Activations Density 0.023%

    No Known Activations