© 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. 4197
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or condemnation, especially in a moral sense

    oai_token-act-pair · gpt-3.5-turbo

    words associated with concepts of justification or rationale

    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
     dust
    -0.72
     swirl
    -0.67
     churn
    -0.66
     Mau
    -0.63
     del
    -0.63
     booster
    -0.63
     tut
    -0.61
     sp
    -0.60
     USA
    -0.59
     promo
    -0.59
    POSITIVE LOGITS
    ensible
    4.47
    ensibly
    2.49
    ensable
    1.54
    ensical
    1.26
    enegger
    1.14
    ensive
    1.13
    ENDED
    1.10
    ensional
    1.08
    ended
    1.08
    ausible
    1.06
    Activations Density 0.016%

    No Known Activations