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. 1-RES-JB
    6. 1421
    Prev
    Next
    INDEX
    Explanations

    proper nouns like names such as "Conan" and "Joan"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly 'Conan' and 'Joan'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achev
    -0.86
    ertodd
    -0.85
    atoon
    -0.74
    oby
    -0.71
    achu
    -0.71
    acca
    -0.70
    ramid
    -0.70
    ettel
    -0.69
    ached
    -0.68
    ystem
    -0.66
    POSITIVE LOGITS
    tons
    1.04
    uin
    0.87
    ãĥĥãĥĪ
    0.80
    Nap
    0.79
    ality
    0.73
    ahime
    0.72
    AAF
    0.70
    ts
    0.67
    ileen
    0.67
    iste
    0.66
    Activations Density 0.029%

    No Known Activations