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. 7-RES-JB
    6. 16083
    Prev
    Next
    INDEX
    Explanations

    references to the Olympics and athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to Olympians and related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hammer
    -0.67
     indictment
    -0.66
     aspiration
    -0.64
     lodge
    -0.64
     Strauss
    -0.61
     charge
    -0.61
     Charge
    -0.61
     sensitivity
    -0.60
     Turtle
    -0.60
     flats
    -0.60
    POSITIVE LOGITS
    iation
    1.44
    iop
    1.41
    iated
    1.40
    iate
    1.30
    ially
    1.28
    iological
    1.26
    iology
    1.24
    iates
    1.24
    iator
    1.22
    icals
    1.22
    Activations Density 0.056%

    No Known Activations