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. 4-RES-JB
    6. 15103
    Prev
    Next
    INDEX
    Explanations

    names or surnames containing 'ott' in them

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific name or term associated with individuals, particularly "ott."

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

    No Comments

    Negative Logits
    senal
    -0.76
    ĺħ
    -0.68
    SOURCE
    -0.67
     lapse
    -0.65
    xual
    -0.65
     calculus
    -0.64
     cooker
    -0.62
    nesota
    -0.59
    lda
    -0.58
     captivity
    -0.58
    POSITIVE LOGITS
    sburgh
    1.10
    awa
    1.05
    leneck
    1.00
    ott
    0.96
    erer
    0.93
    icles
    0.93
    ail
    0.92
    emo
    0.91
    aways
    0.91
    alia
    0.90
    Activations Density 0.007%

    No Known Activations