Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 13808
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Doctor" within various contexts related to the TV show Doctor Who

    oai_token-act-pair · gpt-3.5-turbo

    mentions of characters from the Doctor Who series

    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
     actionGroup
    -0.88
    FUL
    -0.72
     dispersed
    -0.67
     envelope
    -0.65
    perm
    -0.65
     chorus
    -0.64
    restricted
    -0.63
     temp
    -0.63
    HUD
    -0.62
    rig
    -0.61
    POSITIVE LOGITS
     Who
    0.90
    sonian
    0.89
    ysis
    0.85
    abase
    0.83
     Doctor
    0.81
     Strange
    0.79
    acies
    0.76
    ologist
    0.75
    ocide
    0.75
    iatus
    0.74
    Activations Density 0.017%

    No Known Activations