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. 9764
    Prev
    Next
    INDEX
    Explanations

    words related to institutions, organizations, and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific names or titles, particularly those associated with Bantam publications

    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
    holes
    -0.83
    ionage
    -0.72
    wich
    -0.72
     sclerosis
    -0.68
    hole
    -0.68
     ubiqu
    -0.65
     Mandela
    -0.63
    umpy
    -0.62
     happiest
    -0.62
     embr
    -0.62
    POSITIVE LOGITS
    avan
    0.92
    antam
    0.92
    ãĥ¥
    0.90
    weights
    0.84
    ategory
    0.83
    chio
    0.81
    agh
    0.81
    ãĥĥãĤ¯
    0.80
    ãĥ£
    0.79
    pole
    0.77
    Activations Density 0.034%

    No Known Activations