© 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. 6-RES-JB
    11. 12060
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions, particularly neurological abnormalities

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical sentiments expressed in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.75
    ings
    -0.67
     investigative
    -0.67
    INGS
    -0.63
     Illum
    -0.63
     Fitzgerald
    -0.63
    uffy
    -0.62
     Ripple
    -0.61
     Boone
    -0.61
     Wong
    -0.61
    POSITIVE LOGITS
    economic
    1.00
    centric
    0.99
    deal
    0.98
    series
    0.95
    tra
    0.92
    hazard
    0.92
    social
    0.91
     Advertisement
    0.90
    compatible
    0.90
    induced
    0.89
    Activations Density 0.100%

    No Known Activations