© 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. 6-RES-JB
    11. 13776
    Prev
    Next
    INDEX
    Explanations

    names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    word forms indicating names or identifiers of individuals

    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
     shorth
    -0.71
     subscript
    -0.66
    Scotland
    -0.60
     demoral
    -0.59
    Tokens
    -0.57
     plural
    -0.56
    Prim
    -0.56
    FIX
    -0.56
     overwhelming
    -0.55
     corrid
    -0.55
    POSITIVE LOGITS
     Jr
    1.10
    oulos
    1.01
    oglu
    1.00
    enegger
    0.96
    opoulos
    0.92
    owski
    0.90
    zyk
    0.88
     III
    0.88
    ewski
    0.86
     Sr
    0.86
    Activations Density 0.338%

    No Known Activations