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. 3804
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics and rankings

    oai_token-act-pair · gpt-3.5-turbo
    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
    hops
    -0.76
    usa
    -0.75
    internal
    -0.75
    Interstitial
    -0.75
    peak
    -0.72
    EVA
    -0.70
    ICE
    -0.67
    akedown
    -0.67
    IFA
    -0.67
    AppData
    -0.66
    POSITIVE LOGITS
     youngster
    1.26
     Frenchman
    1.22
     veteran
    1.20
     rapper
    1.20
     singer
    1.20
     actor
    1.20
     former
    1.20
     musician
    1.18
     filmmaker
    1.11
     elder
    1.11
    Activations Density 0.516%

    No Known Activations