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. 1303
    Prev
    Next
    INDEX
    Explanations

    terms related to the city or concept of "York"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ork" in various contexts

    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
    ples
    -0.77
     charity
    -0.63
    âĸ¬âĸ¬
    -0.63
    inav
    -0.62
     Bethesda
    -0.61
     tradem
    -0.60
     vanilla
    -0.60
    ciples
    -0.59
    TRY
    -0.59
    ection
    -0.58
    POSITIVE LOGITS
    ansas
    1.23
    ozy
    1.01
    crew
    0.96
    heimer
    0.96
    lift
    0.94
    atana
    0.86
    hire
    0.86
    owski
    0.85
    rait
    0.84
    asus
    0.83
    Activations Density 0.015%

    No Known Activations