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. 6-RES-JB
    6. 13222
    Prev
    Next
    INDEX
    Explanations

    phrases related to databases or digital platforms, particularly those related to specific codes or names such as PD

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or abbreviation labeled "PD."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppo
    -1.01
    hold
    -0.89
    bourg
    -0.83
    holding
    -0.74
    glers
    -0.73
    ãĤ¤ãĥĪ
    -0.73
    ships
    -0.69
    ansas
    -0.68
    ishi
    -0.68
    itud
    -0.68
    POSITIVE LOGITS
    iamond
    0.98
    ouble
    0.94
    GF
    0.92
    oodle
    0.88
    PD
    0.84
    ATES
    0.80
    ragon
    0.79
    illon
    0.79
    insula
    0.78
    ynasty
    0.77
    Activations Density 0.020%

    No Known Activations