Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1676
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    less than or equal to symbols, particularly the "<" character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    opening angle bracket

    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -1.00
    ModLoader
    -0.98
     deported
    -0.79
    wagen
    -0.77
     deportation
    -0.77
    å£
    -0.76
    liga
    -0.74
     administr
    -0.73
     denial
    -0.71
    د
    -0.70
    POSITIVE LOGITS
    span
    1.08
    _>
    0.99
    church
    0.85
    meta
    0.83
    !--
    0.80
    img
    0.78
    std
    0.76
    lambda
    0.76
    ><
    0.74
    insert
    0.72
    Activations Density 0.010%

    No Known Activations