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. 19660
    Prev
    Next
    INDEX
    Explanations

    terms related to camera lenses and film attributes

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

    proper nouns related to photography equipment and techniques

    oai_token-act-pair · gpt-3.5-turbo
    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
     rooft
    -0.65
    Priv
    -0.64
    wcs
    -0.61
     Jagu
    -0.61
    cheat
    -0.61
     Poles
    -0.60
     blot
    -0.60
    soDeliveryDate
    -0.60
    groups
    -0.59
    oby
    -0.59
    POSITIVE LOGITS
    ruary
    1.06
    tein
    0.90
    acci
    0.82
    igi
    0.74
    aux
    0.73
    ushima
    0.73
    illet
    0.70
    enza
    0.68
    ktop
    0.68
    ieri
    0.66
    Activations Density 0.639%

    No Known Activations