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. 4447
    Prev
    Next
    INDEX
    Explanations

    terms related to sports teams and their activities

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and their related aspects

    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
    vasive
    -0.66
     Blumenthal
    -0.66
    romy
    -0.64
    Pic
    -0.64
     stalk
    -0.64
    croft
    -0.61
    Reuters
    -0.61
    Tube
    -0.61
    igmat
    -0.59
     Signs
    -0.59
    POSITIVE LOGITS
     coaches
    0.77
    akeru
    0.77
    hesion
    0.72
    orses
    0.71
    issors
    0.71
     relegation
    0.68
    iets
    0.67
     preseason
    0.66
     Plays
    0.64
     scouts
    0.64
    Activations Density 0.526%

    No Known Activations