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. 10-RES-JB
    6. 12998
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbal phrases related to statements or quotations

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "he" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veter
    -0.70
     Network
    -0.61
     pregn
    -0.61
     Mile
    -0.60
     Gems
    -0.60
     cannabin
    -0.59
     Royale
    -0.59
     Impact
    -0.58
     Components
    -0.58
     Observer
    -0.58
    POSITIVE LOGITS
    zbollah
    1.35
    resy
    1.35
    ctor
    1.26
    uristic
    1.25
    eding
    1.25
    ctic
    1.24
    aping
    1.21
    aped
    1.21
    aps
    1.18
    avier
    1.18
    Activations Density 0.233%

    No Known Activations