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. 2271
    Prev
    Next
    INDEX
    Explanations

    phrases where people are talking or interacting with each other

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun 'he' used in various contexts

    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
    display
    -0.67
    committee
    -0.65
     Bahrain
    -0.65
    anking
    -0.65
    uits
    -0.64
    iliate
    -0.64
    aiman
    -0.64
    Represent
    -0.64
    reshold
    -0.63
    ilateral
    -0.62
    POSITIVE LOGITS
    eded
    1.07
    'll
    1.05
    'd
    1.03
     Majesty
    0.98
    zbollah
    0.98
    resy
    0.94
    mos
    0.90
    eding
    0.82
    pherd
    0.78
    ctor
    0.77
    Activations Density 0.305%

    No Known Activations