Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19392
    Prev
    Next
    INDEX
    Explanations

    words related to social relationships and interactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social and cultural concepts

    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
    drops
    -0.79
    MER
    -0.78
    hands
    -0.76
    fighters
    -0.76
    girls
    -0.75
    fighter
    -0.71
     beating
    -0.68
    smanship
    -0.67
    strings
    -0.66
    falls
    -0.65
    POSITIVE LOGITS
    oci
    1.25
    ociation
    1.06
    ociate
    1.03
    ative
    1.01
    atives
    0.99
    ativity
    0.97
    ationally
    0.90
    atform
    0.89
    omal
    0.88
     associations
    0.88
    Activations Density 0.021%

    No Known Activations