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. 13229
    Prev
    Next
    INDEX
    Explanations

    names of a particular football manager

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable football managers, particularly Pep Guardiola

    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
    lift
    -0.88
    orage
    -0.79
    erala
    -0.79
    Alien
    -0.76
    WARD
    -0.73
    fram
    -0.73
    semble
    -0.72
    ngth
    -0.72
    mble
    -0.72
    yip
    -0.70
    POSITIVE LOGITS
     Guardiola
    1.26
     Pep
    1.03
    sburg
    0.83
    ijn
    0.75
    ause
    0.73
    opard
    0.73
    eters
    0.71
    zek
    0.71
     Clicker
    0.70
    inho
    0.70
    Activations Density 0.011%

    No Known Activations