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. 2-RES-JB
    6. 17009
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to statements

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iries
    -0.65
    display
    -0.64
     Bearing
    -0.63
    iframe
    -0.63
     Seym
    -0.62
    history
    -0.62
     Pastebin
    -0.59
    ا
    -0.58
     equate
    -0.57
    etheless
    -0.57
    POSITIVE LOGITS
     Majesty
    1.02
    zbollah
    0.99
    resy
    0.87
    eded
    0.86
    mos
    0.78
    ALTH
    0.77
    'd
    0.75
    bert
    0.75
    ather
    0.71
     majesty
    0.70
    Activations Density 0.422%

    No Known Activations