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. 13927
    Prev
    Next
    INDEX
    Explanations

    words related to contouring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cont" and its variations, indicating continuous or ongoing actions or states

    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
    BSD
    -0.80
    BuyableInstoreAndOnline
    -0.76
    cffffcc
    -0.70
    MQ
    -0.68
    ħĭ
    -0.67
    ãĤ¬
    -0.67
    EStream
    -0.66
    ï¸
    -0.65
     shed
    -0.65
     Sunshine
    -0.64
    POSITIVE LOGITS
    ented
    1.04
    rast
    1.01
    rived
    0.99
    ortion
    0.96
    rive
    0.95
    acts
    0.94
    rovers
    0.94
    oso
    0.94
    ain
    0.93
    oured
    0.92
    Activations Density 0.011%

    No Known Activations