© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7240
    Prev
    Next
    INDEX
    Explanations

    words related to political and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    words concerning complex social dynamics and interpersonal relationships

    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
     Lines
    -0.57
     Common
    -0.53
     Balanced
    -0.52
     Jav
    -0.52
     Pyramid
    -0.51
     Honour
    -0.51
     Wiz
    -0.51
     Own
    -0.51
     Matter
    -0.50
     Sands
    -0.49
    POSITIVE LOGITS
    geoning
    0.60
    asses
    0.56
    asing
    0.55
    raft
    0.54
    autical
    0.54
    ishly
    0.53
    urch
    0.53
    asers
    0.53
    kered
    0.53
    hed
    0.53
    Activations Density 0.566%

    No Known Activations