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. 7-RES-JB
    6. 3390
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ARM" with various activations, possibly related to ARM processors or other contexts where the term "ARM" appears

    oai_token-act-pair · gpt-3.5-turbo

    references to ARM architecture or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vide
    -0.64
    ween
    -0.62
    ©¶æ
    -0.60
     mask
    -0.60
    WAY
    -0.58
     Pluto
    -0.58
     elig
    -0.57
     Chaff
    -0.57
     Seasons
    -0.57
     lit
    -0.57
    POSITIVE LOGITS
    ageddon
    1.26
    ament
    1.19
    chair
    1.06
    stadt
    1.06
    aments
    1.00
    aceutical
    0.98
    ando
    0.92
    ments
    0.91
    strong
    0.91
    guards
    0.89
    Activations Density 0.021%

    No Known Activations