© 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. 10296
    Prev
    Next
    INDEX
    Explanations

    words indicating caution or wariness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to caution or wariness

    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
    Lay
    -0.75
    eret
    -0.73
    alter
    -0.70
    Tes
    -0.70
    Ultimate
    -0.69
    Interstitial
    -0.69
    lat
    -0.69
    è¦ļéĨĴ
    -0.68
    LAN
    -0.68
    ultimate
    -0.68
    POSITIVE LOGITS
     cautious
    0.90
     wary
    0.86
     optimistic
    0.83
     lest
    0.81
     hesitant
    0.80
     optimism
    0.76
     hesitation
    0.73
     undermin
    0.71
     prag
    0.70
     approach
    0.69
    Activations Density 0.028%

    No Known Activations