© 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. 9661
    Prev
    Next
    INDEX
    Explanations

    words related to surprise or surprising events

    oai_token-act-pair · gpt-3.5-turbo

    words related to surrender or submission

    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
    •layer 4 - surprise

    No Comments

    Negative Logits
    icals
    -0.76
    opathic
    -0.71
    ICAL
    -0.71
    itsch
    -0.70
    ioch
    -0.66
    naires
    -0.65
     menstrual
    -0.65
     cloves
    -0.64
    hetti
    -0.64
    opathy
    -0.63
    POSITIVE LOGITS
    mounted
    1.06
    fer
    0.94
    rounded
    0.94
    mount
    0.93
    geon
    0.92
    geons
    0.90
    tro
    0.89
    lation
    0.88
    sur
    0.86
     sur
    0.84
    Activations Density 0.007%

    No Known Activations