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. 18858
    Prev
    Next
    INDEX
    Explanations

    dates in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    instances of missing persons and related police activities

    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
     Squadron
    -0.64
     cabinets
    -0.62
    fusc
    -0.60
     deduct
    -0.60
     Orbit
    -0.59
     Intermediate
    -0.59
     Spectrum
    -0.59
     coins
    -0.58
     handles
    -0.58
    Spect
    -0.57
    POSITIVE LOGITS
    WASHINGTON
    1.08
    LOS
    0.83
    HCR
    0.83
    EVA
    0.79
    SAN
    0.79
    celona
    0.79
    ccording
    0.78
    ASHINGTON
    0.74
    hesda
    0.73
    eport
    0.73
    Activations Density 0.699%

    No Known Activations