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. 3614
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals holding official positions or titles within an organization

    oai_token-act-pair · gpt-3.5-turbo

    references to membership or membership roles in organizations

    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
    omsday
    -0.91
    iasm
    -0.87
    uca
    -0.72
    chem
    -0.70
    beans
    -0.69
    acs
    -0.68
    Pacific
    -0.67
    uration
    -0.65
     Nieto
    -0.65
    rir
    -0.64
    POSITIVE LOGITS
     Member
    3.06
    Member
    1.77
     VAT
    1.08
     UEFA
    1.04
     Directive
    1.01
     Gentleman
    1.01
     Column
    0.96
     Step
    0.93
     Lie
    0.89
    Offline
    0.87
    Activations Density 0.047%

    No Known Activations