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. 11130
    Prev
    Next
    INDEX
    Explanations

    proper names related to people, specifically the name "Sharon"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Aaron" and its variations

    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
    rity
    -0.81
    matic
    -0.73
    ĻĤ
    -0.73
    ¥ŀ
    -0.73
    ntil
    -0.72
    oresc
    -0.71
    lished
    -0.70
    aternity
    -0.70
    changes
    -0.65
    mable
    -0.65
    POSITIVE LOGITS
    aron
    1.08
    inian
    1.00
    ée
    0.86
    onne
    0.83
    esses
    0.83
    ette
    0.81
     rabbi
    0.80
     Sharon
    0.79
     Levant
    0.78
    iel
    0.75
    Activations Density 0.006%

    No Known Activations