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. 5649
    Prev
    Next
    INDEX
    Explanations

    mentions of medical or scientific terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms related to a comic shop and its owner

    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
     Tackle
    -0.73
     Wall
    -0.70
    kers
    -0.70
     Booker
    -0.69
     Kardashian
    -0.64
     stern
    -0.64
     Goldman
    -0.64
     FTC
    -0.63
     Advent
    -0.62
     Davis
    -0.62
    POSITIVE LOGITS
    alg
    1.77
    algia
    1.08
    alsa
    0.92
    rowth
    0.90
    cffffcc
    0.84
    amation
    0.81
    hes
    0.79
    omorph
    0.78
    emet
    0.78
    omach
    0.78
    Activations Density 0.015%

    No Known Activations