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. 5836
    Prev
    Next
    INDEX
    Explanations

    instances of records being broken or specific records being set

    oai_token-act-pair · gpt-3.5-turbo

    references to world records, particularly those associated with Guinness

    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
    cemic
    -0.74
    sei
    -0.65
    itas
    -0.64
    fa
    -0.64
    cation
    -0.64
    ocate
    -0.63
    endez
    -0.62
    umat
    -0.61
    cery
    -0.60
    aughter
    -0.60
    POSITIVE LOGITS
     record
    0.91
     breaker
    0.87
     holder
    0.81
     Record
    0.79
     records
    0.75
    Maximum
    0.74
     Breaker
    0.71
     achievement
    0.70
     Keeper
    0.69
    IRD
    0.69
    Activations Density 0.036%

    No Known Activations