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. 8304
    Prev
    Next
    INDEX
    Explanations

    words related to software and technology updates

    oai_token-act-pair · gpt-3.5-turbo

    references to firmware and related technical terms

    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
    nered
    -0.77
    adult
    -0.73
    xon
    -0.72
    ulhu
    -0.67
    ivas
    -0.67
    xus
    -0.66
     Dumb
    -0.66
    water
    -0.66
    hur
    -0.65
    othing
    -0.65
    POSITIVE LOGITS
     firmware
    1.40
     upd
    0.86
     calibration
    0.84
     upgr
    0.84
     BIOS
    0.82
     calibr
    0.81
     chipset
    0.81
     circuitry
    0.81
     specifications
    0.77
     modem
    0.76
    Activations Density 0.009%

    No Known Activations