© 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. 7-RES-JB
    11. 1519
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "sur-" indicating an element of surprise or exceeding

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sur" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAL
    -0.77
    opathic
    -0.72
    imore
    -0.71
    icals
    -0.71
    itsch
    -0.65
     Doctors
    -0.63
    ICE
    -0.62
    OWN
    -0.62
     Away
    -0.61
     tense
    -0.61
    POSITIVE LOGITS
    mounted
    1.16
    mount
    1.08
    charge
    0.97
    fer
    0.96
    charg
    0.90
    charged
    0.88
    lim
    0.88
    geon
    0.88
    rounded
    0.87
    geons
    0.86
    Activations Density 0.011%

    No Known Activations