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. 16130
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and government policies or programs

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various systems and practices, particularly in governance and health care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pora
    -0.76
    irlf
    -0.75
    Alias
    -0.73
    RAW
    -0.71
    cius
    -0.70
    aido
    -0.67
    emet
    -0.65
    olls
    -0.65
    ideo
    -0.65
    OST
    -0.64
    POSITIVE LOGITS
    tenance
    0.89
     hybrid
    0.85
     hybrids
    0.83
    roying
    0.76
    osterone
    0.76
    ning
    0.75
     extraord
    0.73
    rior
    0.71
     complexes
    0.68
    quartered
    0.67
    Activations Density 0.252%

    No Known Activations