Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21274
    Prev
    Next
    INDEX
    Explanations

    mention of curves, typically related to data analysis or patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of curves in data analysis and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.70
     WATCHED
    -0.69
    ynski
    -0.69
    orians
    -0.66
    aples
    -0.65
    oral
    -0.65
    photos
    -0.64
    @#&
    -0.64
     Duty
    -0.64
     Ans
    -0.64
    POSITIVE LOGITS
    balls
    1.18
     curve
    1.06
     Curve
    0.98
     curves
    0.98
    ball
    0.92
     curv
    0.83
    atism
    0.82
     slope
    0.81
    kered
    0.80
    gradient
    0.77
    Activations Density 0.006%

    No Known Activations