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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 115
    Prev
    Next
    INDEX
    Explanations

    terms related to bodily functions, specifically urination

    oai_token-act-pair · gpt-3.5-turbo

    references to life-threatening situations

    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
    OIL
    -0.77
     LOT
    -0.73
    ONS
    -0.73
    rek
    -0.72
    tons
    -0.72
    eric
    -0.70
    \\\\\\\\
    -0.69
    å¼
    -0.67
    Sean
    -0.66
     Riders
    -0.65
    POSITIVE LOGITS
     stray
    0.75
     comma
    0.68
     isolate
    0.67
     subdiv
    0.67
    onga
    0.67
     recognise
    0.66
     hone
    0.65
    aram
    0.65
     honoured
    0.63
     investigate
    0.63
    Activations Density 0.000%

    No Known Activations