© 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. 1-RES-JB
    11. 16383
    Prev
    Next
    INDEX
    Explanations

    careful actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "careful."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anon
    -0.77
    Phones
    -0.71
    Wars
    -0.71
    Pear
    -0.71
    NZ
    -0.70
    flat
    -0.70
    ifles
    -0.68
    AF
    -0.67
    CBC
    -0.67
     Ethiopia
    -0.67
    POSITIVE LOGITS
     careful
    1.08
     scrutiny
    0.96
    autions
    0.88
     cautious
    0.84
     precautions
    0.82
     calibr
    0.80
     heed
    0.79
     attentive
    0.79
     precaution
    0.78
     stewards
    0.77
    Activations Density 0.006%

    No Known Activations