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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 16496
    Prev
    Next
    INDEX
    Explanations

    height and weight measurements of individuals

    oai_token-act-pair · gpt-3.5-turbo

    information related to heights and weights, particularly in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ezvous
    -0.77
     extinction
    -0.74
     cac
    -0.71
    orescence
    -0.71
    eele
    -0.69
    heit
    -0.65
    arak
    -0.65
    ciating
    -0.64
    peak
    -0.64
    hower
    -0.63
    POSITIVE LOGITS
    Runner
    0.90
    INGTON
    0.76
     ILCS
    0.74
    Ball
    0.73
    inches
    0.72
    feet
    0.72
     brass
    0.70
    Steel
    0.70
    waukee
    0.69
    oval
    0.69
    Activations Density 0.077%

    No Known Activations