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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20757
    Prev
    Next
    INDEX
    Explanations

    mentions of specific towns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'Town' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utic
    -0.90
    terday
    -0.86
    nces
    -0.82
    uberty
    -0.81
    aunder
    -0.81
    issance
    -0.80
    utics
    -0.79
    ulously
    -0.71
    ances
    -0.70
    etheus
    -0.69
    POSITIVE LOGITS
    folk
    1.13
    spe
    1.13
    ships
    1.01
    house
    1.00
     Halls
    0.95
    houses
    0.95
    send
    0.86
    she
    0.86
    ship
    0.85
    scape
    0.85
    Activations Density 0.016%

    No Known Activations