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. 9-RES-JB
    6. 10891
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ari" in different contexts, potentially focusing on the repetition of the name in various sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ari."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.72
    sung
    -0.70
    lasses
    -0.70
    ted
    -0.70
    umbledore
    -0.68
    fulness
    -0.67
    eatures
    -0.66
    mort
    -0.65
    lights
    -0.62
    meet
    -0.62
    POSITIVE LOGITS
    yah
    1.19
    ya
    1.10
    ño
    1.02
    Äĩ
    0.99
    YA
    0.88
    asis
    0.85
     Vaj
    0.85
    asing
    0.83
    yy
    0.83
    ksh
    0.83
    Activations Density 0.061%

    No Known Activations