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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 2926
    Prev
    Next
    INDEX
    Explanations

    options or choices presented to users

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "choose" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amia
    -0.77
    kefeller
    -0.70
    acan
    -0.68
    ForgeModLoader
    -0.68
    WARN
    -0.67
    uzz
    -0.67
    DEF
    -0.64
    bley
    -0.64
    oil
    -0.62
    Ball
    -0.61
    POSITIVE LOGITS
     wisely
    0.88
    axe
    0.87
     whether
    0.84
     sides
    0.83
     choices
    0.80
     between
    0.77
     options
    0.76
     choose
    0.76
     answ
    0.72
     selections
    0.70
    Activations Density 0.063%

    No Known Activations