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. 0-RES-JB
    6. 24097
    Prev
    Next
    INDEX
    Explanations

    references to a specific suffix or group of characters, "ix"

    oai_token-act-pair · gpt-3.5-turbo

    unique identifiers or names, particularly those related to specific entities or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brah
    -0.66
     bapt
    -0.65
     congratulations
    -0.65
     inspiration
    -0.65
     journalistic
    -0.63
     alarm
    -0.62
    ãģ®å®
    -0.62
     srfAttach
    -0.62
     halfway
    -0.62
    rats
    -0.61
    POSITIVE LOGITS
    ix
    4.41
    IX
    2.53
    ixed
    1.58
    ixt
    1.46
    ux
    1.45
    yx
    1.45
    ax
    1.37
    iq
    1.31
    ixir
    1.29
    ixel
    1.25
    Activations Density 0.019%

    No Known Activations