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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13824
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly those associated with political or media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifier
    -0.76
     dstg
    -0.66
    ifiers
    -0.65
    semble
    -0.64
    ften
    -0.64
    76561
    -0.62
     Bulgarian
    -0.61
     Bulgar
    -0.60
     WTO
    -0.60
    orative
    -0.59
    POSITIVE LOGITS
     Fitzgerald
    1.18
    gerald
    1.16
    patrick
    0.82
     Gallagher
    0.82
    olini
    0.82
    etta
    0.75
    ranch
    0.72
    weed
    0.71
     Duffy
    0.70
     Stout
    0.69
    Activations Density 0.013%

    No Known Activations