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. 3-RES-JB
    6. 18944
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to identifying or classification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to identification and classification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bakr
    -0.80
    OPLE
    -0.76
     Spice
    -0.70
     turkey
    -0.70
     coli
    -0.70
     Skywalker
    -0.69
     initiation
    -0.67
    PLIED
    -0.66
     Nile
    -0.65
     Oaks
    -0.65
    POSITIVE LOGITS
    ifying
    1.86
    ifications
    1.83
    ified
    1.76
    ifies
    1.72
    ification
    1.64
    ifier
    1.64
    ifiers
    1.62
    ifiable
    1.59
    ific
    1.46
    ify
    1.42
    Activations Density 0.020%

    No Known Activations