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. 13154
    Prev
    Next
    INDEX
    Explanations

    mentions of outdoor sports and activities, particularly related to individual achievements and competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to paralyzed athletes and their sports

    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
     informants
    -0.71
    reve
    -0.66
    holes
    -0.64
     backdoor
    -0.61
     Bezos
    -0.60
    awatts
    -0.60
    ulet
    -0.60
    contained
    -0.59
    ifice
    -0.59
     informant
    -0.59
    POSITIVE LOGITS
    bike
    1.14
     biking
    1.05
     cycling
    1.00
     racing
    1.00
     bikes
    0.97
     cyclist
    0.95
     bike
    0.95
     Bike
    0.95
     doping
    0.95
     endurance
    0.94
    Activations Density 0.376%

    No Known Activations