© 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
    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. 12246
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or a state of suspense

    oai_token-act-pair · gpt-3.5-turbo

    terms related to uncertainty and unstable situations

    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
    otte
    -0.78
    enne
    -0.78
    ithe
    -0.78
    atures
    -0.75
    atts
    -0.75
    ivation
    -0.74
    aviour
    -0.73
    antis
    -0.72
    iber
    -0.71
    Ps
    -0.71
    POSITIVE LOGITS
    manship
    0.89
    locks
    0.84
     jeopardy
    0.79
    lock
    0.76
     Yose
    0.71
    locked
    0.70
    lein
    0.67
    stadt
    0.67
     Schr
    0.66
    tie
    0.65
    Activations Density 0.029%

    No Known Activations