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. 3-RES-JB
    6. 10185
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the name "Arn" and other similar names like "Arnall", "Arnold", as well as specific locations like "Nottingham"

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns, particularly related to individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.73
    edly
    -0.68
    ing
    -0.67
    eer
    -0.63
    ĺħ
    -0.62
    ¤
    -0.60
    ples
    -0.60
     coerc
    -0.59
     Parenthood
    -0.59
    «ĺ
    -0.59
    POSITIVE LOGITS
    emis
    0.89
    icas
    0.84
    ica
    0.81
    adeon
    0.80
    oken
    0.79
    oker
    0.78
    arts
    0.78
    gy
    0.77
    ically
    0.77
    FORE
    0.77
    Activations Density 0.036%

    No Known Activations