© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15266
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Collins."

    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
     discrep
    -0.78
    inished
    -0.72
    ICAN
    -0.69
    ETA
    -0.69
    ilitation
    -0.68
     hoc
    -0.63
    ocard
    -0.63
    iddled
    -0.62
    otor
    -0.61
    OOD
    -0.61
    POSITIVE LOGITS
    worth
    1.14
     Collins
    0.97
    ively
    0.87
    mount
    0.85
    ville
    0.79
     Andersen
    0.77
    es
    0.76
    Collins
    0.72
     Hancock
    0.71
    ision
    0.70
    Activations Density 0.022%

    No Known Activations