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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 20098
    Prev
    Next
    INDEX
    Explanations

    phrases related to newness and freshness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize contrasts between old and new concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laksh
    -0.78
     Lau
    -0.70
    tackle
    -0.69
    gross
    -0.63
    ibaba
    -0.63
    >>\
    -0.62
    ortion
    -0.62
    ebin
    -0.62
    romy
    -0.59
     Shots
    -0.59
    POSITIVE LOGITS
     new
    1.61
     old
    1.60
     newer
    1.54
    new
    1.37
     originals
    1.27
     anew
    1.27
     unchanged
    1.27
     older
    1.26
     existing
    1.25
     refreshed
    1.23
    Activations Density 0.758%

    No Known Activations