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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 4932
    Prev
    Next
    INDEX
    Explanations

    phrases related to universities, student unions, health insurance, student press, student protests, and related administrative and policy terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to student advocacy and organizational structures

    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
    âķIJâķIJ
    -0.88
    ãĥ¯ãĥ³
    -0.81
    âĸ¬âĸ¬
    -0.77
    å§«
    -0.73
    Downloadha
    -0.72
    Interstitial
    -0.71
    Reloaded
    -0.68
    Ö
    -0.68
     Arrows
    -0.66
     attm
    -0.66
    POSITIVE LOGITS
    mage
    0.68
     waivers
    0.65
    escription
    0.64
    reciation
    0.64
    slave
    0.64
    iaries
    0.64
    onomy
    0.62
    emo
    0.60
    sts
    0.60
    assi
    0.58
    Activations Density 0.562%

    No Known Activations