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. 0-RES-JB
    6. 21370
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms with 'OH'

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "OH," likely identifying references related to Ohio

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proced
    -0.69
     multicultural
    -0.64
    brance
    -0.63
     Adapt
    -0.62
     Chimera
    -0.60
     communal
    -0.60
     Tes
    -0.60
     fanc
    -0.59
     speculative
    -0.59
     counters
    -0.59
    POSITIVE LOGITS
    OH
    4.46
     OH
    2.03
    oh
    1.57
    Ohio
    1.50
    OSH
    1.39
    OF
    1.36
    HO
    1.30
    NH
    1.28
    RH
    1.27
    OO
    1.26
    Activations Density 0.012%

    No Known Activations