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. 10-RES-JB
    6. 11906
    Prev
    Next
    INDEX
    Explanations

    terms related to abbreviations or acronyms followed by their expansions

    oai_token-act-pair · gpt-3.5-turbo

    references to various statistical or legal entities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Never
    -0.70
    Synopsis
    -0.66
    engine
    -0.65
    rue
    -0.65
    erald
    -0.65
    obile
    -0.65
    abre
    -0.64
    retch
    -0.64
    estern
    -0.63
    vable
    -0.63
    POSITIVE LOGITS
     GD
    0.97
     EB
    0.96
     SQ
    0.92
     COP
    0.90
     MAP
    0.90
     MO
    0.89
     MC
    0.88
     MF
    0.88
     MUS
    0.87
     ES
    0.87
    Activations Density 0.084%

    No Known Activations