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. 22021
    Prev
    Next
    INDEX
    Explanations

    instances where players are being signed to sports teams

    oai_token-act-pair · gpt-3.5-turbo

    words related to player signings in sports contexts

    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
    ĸļ
    -0.71
    perty
    -0.69
    winter
    -0.69
    borough
    -0.66
     Oliv
    -0.66
     ns
    -0.65
     Circuit
    -0.63
     pul
    -0.63
     COURT
    -0.63
    Panel
    -0.62
    POSITIVE LOGITS
     waivers
    0.88
     signings
    0.83
    */(
    0.82
     signing
    0.81
     Signed
    0.81
    ificantly
    0.79
    ãĥ¼ãĥĨãĤ£
    0.78
     bonuses
    0.77
     contracts
    0.74
    ificant
    0.74
    Activations Density 0.027%

    No Known Activations