© 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. 12627
    Prev
    Next
    INDEX
    Explanations

    references to actions that involve taking something away or depriving something from someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a loss or deprivation of resources

    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
    fried
    -0.72
    >:
    -0.71
    pring
    -0.69
    answered
    -0.69
    ':
    -0.69
     occurrences
    -0.68
    nces
    -0.66
    ï¸ı
    -0.66
     partName
    -0.62
    Disclaimer
    -0.62
    POSITIVE LOGITS
     whom
    0.73
    Ħ¢
    0.72
    idges
    0.69
    umbn
    0.66
     timely
    0.64
    ļéĨĴ
    0.64
    eering
    0.59
     healthcare
    0.59
    ansom
    0.59
    cept
    0.58
    Activations Density 0.809%

    No Known Activations