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. 2-RES-JB
    6. 180
    Prev
    Next
    INDEX
    Explanations

    elements of text that contain the syllable "mer."

    oai_token-act-pair · gpt-4-turbo

    terms related to mergers and acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    references to mergers and specific instances of the term "mer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORY
    -0.74
    ¬¼
    -0.71
     Eleven
    -0.67
    YE
    -0.65
    ONES
    -0.65
     fixed
    -0.65
    ory
    -0.65
    orsche
    -0.63
    »Ĵ
    -0.60
    HAEL
    -0.60
    POSITIVE LOGITS
    cedes
    1.19
    maid
    0.97
    folk
    0.96
    idian
    0.91
     mer
    0.84
     simultane
    0.83
    ited
    0.83
    cial
    0.82
    iously
    0.82
    isse
    0.81
    Activations Density 0.003%

    No Known Activations