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. 11711
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the state of Assam

    oai_token-act-pair · gpt-3.5-turbo

    mentions of an entity or location associated with the term "Assam."

    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
    çĦ
    -0.72
     XD
    -0.72
    vation
    -0.70
     AMA
    -0.68
     Kubrick
    -0.66
    Ïī
    -0.64
    æĸ¹
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    ttes
    -0.62
     Sparkle
    -0.62
    POSITIVE LOGITS
    imilation
    1.36
    essor
    1.24
    umption
    1.22
    ortment
    1.21
    sembly
    1.20
    alon
    1.14
    isted
    1.11
    igned
    1.10
    assin
    1.08
    alam
    1.08
    Activations Density 0.010%

    No Known Activations