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. 12190
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names of people or places, more specifically names containing 'Alf' or 'Alc'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific food-related terms

    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
    ledged
    -0.85
    pload
    -0.82
    achu
    -0.80
    ling
    -0.71
    soDeliveryDate
    -0.71
    ly
    -0.67
    kie
    -0.66
    apore
    -0.66
    pter
    -0.66
     Beware
    -0.66
    POSITIVE LOGITS
    onso
    1.17
    arial
    0.87
    ayne
    0.85
     retri
    0.84
    ibaba
    0.81
    inia
    0.78
    ivia
    0.78
    manac
    0.77
    asca
    0.75
    onde
    0.74
    Activations Density 0.019%

    No Known Activations