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. 6815
    Prev
    Next
    INDEX
    Explanations

    text related to data types and type checking in computer programming

    oai_token-act-pair · gpt-3.5-turbo

    references to data types in programming contexts

    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
    ILLE
    -0.80
     gul
    -0.75
    vous
    -0.73
     Zimmer
    -0.70
    pload
    -0.70
    nesday
    -0.67
    å§«
    -0.66
    romeda
    -0.66
    llah
    -0.64
    aeper
    -0.64
    POSITIVE LOGITS
    faces
    1.34
    face
    1.30
    ahead
    1.13
    casting
    1.08
    alias
    0.95
    etting
    0.88
    etter
    0.85
    classes
    0.84
    ology
    0.81
    cast
    0.79
    Activations Density 0.025%

    No Known Activations