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. 5132
    Prev
    Next
    INDEX
    Explanations

    Italian names

    oai_token-act-pair · gpt-3.5-turbo

    words and names associated with famous directors and filmmakers

    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
    nect
    -0.78
    fman
    -0.77
    ascript
    -0.75
    ĸļ
    -0.73
    earchers
    -0.73
    rf
    -0.72
    clips
    -0.71
    bats
    -0.69
    hound
    -0.69
    ecause
    -0.66
    POSITIVE LOGITS
     Manuel
    1.03
     Werner
    0.98
     Antonio
    0.95
     Gabriel
    0.93
    iano
    0.93
    ovich
    0.92
     Perez
    0.91
     Garcia
    0.90
     Marino
    0.89
     Rodgers
    0.88
    Activations Density 0.262%

    No Known Activations