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. 19071
    Prev
    Next
    INDEX
    Explanations

    numbers related to distances or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to distances, ages, and statistics

    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
     hierarchy
    -0.69
    parency
    -0.69
    ribution
    -0.68
    ventory
    -0.67
    ioch
    -0.62
    TextColor
    -0.61
    orts
    -0.61
    osion
    -0.60
     Dos
    -0.60
    output
    -0.59
    POSITIVE LOGITS
    ½
    1.05
     inches
    0.85
     cents
    0.84
     ½
    0.80
    teenth
    0.80
    inches
    0.79
     shy
    0.75
    een
    0.74
    º
    0.72
    cm
    0.72
    Activations Density 0.125%

    No Known Activations