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. 5-RES-JB
    6. 7982
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of animals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific animal species, particularly big cats and elephants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASED
    -0.68
    Commission
    -0.68
    ALLY
    -0.68
    âĸ¬
    -0.67
    States
    -0.66
    cknow
    -0.66
    Leader
    -0.65
    orie
    -0.65
    nce
    -0.64
    wise
    -0.64
    POSITIVE LOGITS
    aurus
    1.29
    mith
    1.22
    uits
    1.15
    paces
    1.14
    hips
    1.14
    hip
    1.13
    cale
    1.09
    '
    1.06
    pace
    0.99
    ervative
    0.99
    Activations Density 0.108%

    No Known Activations