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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15676
    Prev
    Next
    INDEX
    Explanations

    words containing the letters "es", with a focus on words where "es" appears as a standalone syllable

    oai_token-act-pair · gpt-3.5-turbo
    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
    OSH
    -0.65
    isconsin
    -0.62
    glers
    -0.60
     lifetime
    -0.60
     extrem
    -0.60
    FTWARE
    -0.60
    è»
    -0.59
    sonian
    -0.59
    OGR
    -0.59
    ONSORED
    -0.58
    POSITIVE LOGITS
    ktop
    1.46
    terday
    1.33
    liga
    1.19
    earchers
    1.08
    pec
    1.06
    earch
    1.05
    andro
    1.02
    eeks
    0.99
    ign
    0.98
    eed
    0.97
    Activations Density 0.038%

    No Known Activations