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. 9-RES-JB
    6. 15295
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance evaluation, recognition, or assessment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shown" or "showed" to indicate evidence of talent or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.97
    oldown
    -0.71
    ksh
    -0.71
    chio
    -0.68
    milo
    -0.67
    ades
    -0.67
    idays
    -0.64
    76561
    -0.64
    alez
    -0.64
    minecraft
    -0.64
    POSITIVE LOGITS
     signs
    1.15
     willingness
    1.08
    ered
    1.04
     promise
    0.99
     flashes
    0.93
     resilience
    0.92
     composure
    0.91
     maturity
    0.89
     exceptional
    0.89
     weakness
    0.88
    Activations Density 0.081%

    No Known Activations