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. 3-RES-JB
    6. 19846
    Prev
    Next
    INDEX
    Explanations

    mentions of the formation of groups, organizations, or committees

    oai_token-act-pair · gpt-3.5-turbo

    instances of organizations or groups being established

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    visor
    -0.77
    ILLE
    -0.68
    RESULTS
    -0.67
     Motorsport
    -0.64
    ysis
    -0.63
     McGr
    -0.62
    Rare
    -0.59
     sideline
    -0.58
     Predators
    -0.58
    ily
    -0.58
    POSITIVE LOGITS
    idable
    1.15
    aldehyde
    0.94
    ulates
    0.89
    lehem
    0.87
     alliances
    0.87
    furt
    0.84
     Seym
    0.80
     forming
    0.79
    forms
    0.79
    ulas
    0.77
    Activations Density 0.020%

    No Known Activations