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. 8820
    Prev
    Next
    INDEX
    Explanations

    specific phrases that start with "One of" followed by various descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include "one of" followed by descriptions or identifiers

    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
    ////
    -0.70
    =-=-
    -0.69
    Services
    -0.68
    ENCE
    -0.64
    riages
    -0.63
     fortunes
    -0.62
    ences
    -0.62
    artifacts
    -0.61
    ORTS
    -0.60
     Beir
    -0.59
    POSITIVE LOGITS
    undred
    0.79
    teenth
    0.77
    dozen
    0.75
    ndra
    0.75
    nikov
    0.74
    ieth
    0.72
    GHz
    0.67
    ighty
    0.67
    wich
    0.67
    chev
    0.66
    Activations Density 0.623%

    No Known Activations