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. 10165
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly ones that introduce contrast or additional information

    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
    chairs
    -0.60
     suitcase
    -0.59
     Ike
    -0.59
    om
    -0.54
    AV
    -0.54
     rehearsal
    -0.53
     XV
    -0.53
    bound
    -0.53
    cott
    -0.53
     foreigner
    -0.53
    POSITIVE LOGITS
     nonetheless
    0.87
    âķIJâķIJ
    0.81
     suffice
    0.80
     beware
    0.78
     acknow
    0.77
     alas
    0.77
    ebus
    0.76
     nevertheless
    0.75
     //[
    0.74
     anecd
    0.74
    Activations Density 0.083%

    No Known Activations