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. 5135
    Prev
    Next
    INDEX
    Explanations

    names of individuals related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to the football manager Mauricio Pochettino and related concepts

    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
     Carbuncle
    -0.71
    growth
    -0.71
    carry
    -0.68
     concussion
    -0.66
     Sapphire
    -0.66
     Lilly
    -0.65
     Perspective
    -0.64
     Wonderland
    -0.64
     Breath
    -0.63
    1016
    -0.63
    POSITIVE LOGITS
    icio
    0.98
    ity
    0.86
    aults
    0.84
    itan
    0.84
    acies
    0.82
    ulner
    0.80
     Maur
    0.79
    ines
    0.79
    iments
    0.78
    imil
    0.76
    Activations Density 0.017%

    No Known Activations