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. 5521
    Prev
    Next
    INDEX
    Explanations

    mentions of names or titles with the suffix "amud" or "ron"

    oai_token-act-pair · gpt-3.5-turbo

    names and identifiers associated with prominent individuals

    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
    BILITIES
    -1.02
     sugg
    -0.76
    chio
    -0.69
    escription
    -0.67
    SpaceEngineers
    -0.65
     Millenn
    -0.65
    multipl
    -0.63
    kefeller
    -0.63
    20439
    -0.62
    earable
    -0.62
    POSITIVE LOGITS
     pains
    0.71
     Pradesh
    0.70
    uddin
    0.70
     Salam
    0.68
    schild
    0.68
    lich
    0.68
    ashtra
    0.67
    igans
    0.67
    ients
    0.66
    ipal
    0.65
    Activations Density 0.208%

    No Known Activations