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. 21435
    Prev
    Next
    INDEX
    Explanations

    physical locations and descriptions of settings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods and commas, indicating sentence structure or termination

    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
     estranged
    -0.80
     wedd
    -0.77
     hust
    -0.74
     tink
    -0.73
     deaf
    -0.72
     pan
    -0.70
    xual
    -0.70
    ĸļ
    -0.69
     grop
    -0.68
     scrap
    -0.68
    POSITIVE LOGITS
    soDeliveryDate
    0.94
    Notable
    0.93
    Its
    0.89
    Reader
    0.87
    Example
    0.86
    2018
    0.85
    Current
    0.84
    Prior
    0.84
    Personally
    0.82
    Interest
    0.82
    Activations Density 0.505%

    No Known Activations