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. 6892
    Prev
    Next
    INDEX
    Explanations

    technology-related terms, especially those related to high performance or risk

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk and capacity in various 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
    SPONSORED
    -0.83
    agi
    -0.79
    ãĤ¨ãĥ«
    -0.78
    adier
    -0.73
    =-=-=-=-
    -0.71
    umi
    -0.71
    ften
    -0.69
    alter
    -0.68
    chy
    -0.67
    IGHTS
    -0.66
    POSITIVE LOGITS
     (>
    0.96
     earners
    0.84
     versions
    0.67
     (<
    0.66
     solutions
    0.65
    imensional
    0.65
     residential
    0.63
     Sodium
    0.63
     computing
    0.63
     interval
    0.62
    Activations Density 0.115%

    No Known Activations