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. 11-RES-JB
    6. 19387
    Prev
    Next
    INDEX
    Explanations

    words related to inns or hotels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations or places within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rely
    -0.68
    ques
    -0.67
    ============
    -0.63
    ¶æ
    -0.61
    ========
    -0.60
    Reloaded
    -0.59
     Brief
    -0.59
    flight
    -0.58
    gencies
    -0.57
     brunch
    -0.57
    POSITIVE LOGITS
    ipeg
    1.66
    ovation
    1.52
    ocent
    1.35
    ikuman
    1.33
    osuke
    1.30
    itus
    1.22
    umerable
    1.19
    spir
    1.15
    igan
    1.11
    igans
    1.06
    Activations Density 0.065%

    No Known Activations