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. 2014
    Prev
    Next
    INDEX
    Explanations

    references to community-based services or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with community-based services and organizations

    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
     Mehran
    -0.89
    velt
    -0.75
    ctory
    -0.70
    Reilly
    -0.69
    Matrix
    -0.67
    */(
    -0.67
    Pacific
    -0.66
     thrott
    -0.64
    uma
    -0.64
    catentry
    -0.62
    POSITIVE LOGITS
    giene
    0.79
    population
    0.77
     volunteers
    0.74
     volunteer
    0.69
    awareness
    0.67
    lishes
    0.67
     kindred
    0.67
     Survivors
    0.66
     Volunteers
    0.65
    groups
    0.64
    Activations Density 0.433%

    No Known Activations