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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 22910
    Prev
    Next
    INDEX
    Explanations

    action words related to improvement or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    references to improving or increasing various metrics or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uphem
    -0.77
    olina
    -0.70
    ocument
    -0.69
    oval
    -0.68
    plain
    -0.65
    opus
    -0.65
    ti
    -0.65
    ©¶æ
    -0.65
    £ı
    -0.63
    alin
    -0.63
    POSITIVE LOGITS
     chances
    1.43
     reputation
    1.27
     credibility
    1.20
     credentials
    1.12
     prospects
    1.09
     stature
    1.08
     spirits
    1.06
     fortunes
    1.04
     competitiveness
    1.03
     morale
    1.01
    Activations Density 0.218%

    No Known Activations