Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12568
    Prev
    Next
    INDEX
    Explanations

    verbs related to encountering or discovering something by chance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stumble" and its variations

    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
    cise
    -0.77
    orthern
    -0.74
    atu
    -0.72
     subp
    -0.71
    cell
    -0.70
    umption
    -0.69
    activation
    -0.69
    autical
    -0.68
    cel
    -0.68
    entric
    -0.66
    POSITIVE LOGITS
     stumble
    1.18
     stumbled
    1.02
    weed
    0.96
     stumbling
    0.89
     Mulcair
    0.75
     Corpse
    0.73
     stomp
    0.71
    lehem
    0.71
    ãĥĦ
    0.71
     fumble
    0.70
    Activations Density 0.007%

    No Known Activations