© 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. 3-RES-JB
    11. 13052
    Prev
    Next
    INDEX
    Explanations

    keywords related to controversy or opposing views

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contraband and illegal activities

    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
    HAHA
    -0.78
    BRE
    -0.76
     Zucker
    -0.75
    tale
    -0.73
    teen
    -0.70
     Preservation
    -0.69
    66666666
    -0.69
    #$
    -0.69
    eer
    -0.68
    doms
    -0.67
    POSITIVE LOGITS
    aband
    1.21
     contr
    1.17
    ition
    0.99
    arians
    0.88
    ention
    0.84
    itive
    0.81
    pose
    0.81
    arily
    0.79
    arse
    0.79
    itionally
    0.77
    Activations Density 0.005%

    No Known Activations