© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7256
    Prev
    Next
    INDEX
    Explanations

    words related to caution and warning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to caution and carefulness

    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
    LAN
    -0.82
    Ring
    -0.75
    plex
    -0.74
    Interstitial
    -0.72
    Plex
    -0.71
    frey
    -0.71
    alter
    -0.70
    bleacher
    -0.70
    ACH
    -0.69
    pton
    -0.68
    POSITIVE LOGITS
     cautious
    1.19
     optimism
    1.08
     optimistic
    1.01
     hesitation
    0.90
     approach
    0.86
     cautiously
    0.86
     hesitant
    0.86
     timid
    0.85
     equilibrium
    0.84
     wary
    0.83
    Activations Density 0.012%

    No Known Activations