© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 11820
    Prev
    Next
    INDEX
    Explanations

    references to strictness, structure, or stringent conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structural frameworks or equipment, particularly focusing on "rig" and its variations

    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
     Dot
    -0.79
     Peninsula
    -0.72
     Extrem
    -0.70
    letters
    -0.69
     Cf
    -0.68
     Adults
    -0.67
     Bie
    -0.67
     Fas
    -0.65
     Reach
    -0.63
     Malays
    -0.63
    POSITIVE LOGITS
    orously
    1.54
     rig
    1.31
     rigs
    1.02
     rigged
    0.97
    rig
    0.96
    regor
    0.95
    rador
    0.92
    aton
    0.89
     rigging
    0.87
    iets
    0.87
    Activations Density 0.009%

    No Known Activations