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. 8-RES-JB
    6. 20721
    Prev
    Next
    INDEX
    Explanations

    terms related to file formats and data structures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.84
    hower
    -0.81
    wreck
    -0.81
    imbabwe
    -0.76
    aste
    -0.76
    agen
    -0.75
    agle
    -0.75
    wife
    -0.75
    ONSORED
    -0.74
    alker
    -0.73
    POSITIVE LOGITS
     configurations
    1.13
     warranties
    1.10
     attachments
    1.09
     surgeries
    1.09
     swaps
    1.06
     suspensions
    1.06
     extensions
    1.05
     agreements
    1.04
     contracts
    1.04
     histories
    1.02
    Activations Density 0.346%

    No Known Activations