© 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. 7280
    Prev
    Next
    INDEX
    Explanations

    names of locations, typically cities or regions

    oai_token-act-pair · gpt-3.5-turbo

    the term "har" 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
    psey
    -0.83
     certific
    -0.77
    ortium
    -0.73
    eers
    -0.72
    éĹĺ
    -0.72
     transitional
    -0.72
    essee
    -0.71
    erous
    -0.69
     chalk
    -0.68
     nomine
    -0.68
    POSITIVE LOGITS
    rod
    0.97
    assment
    0.97
    vest
    0.92
    vard
    0.90
    riages
    0.89
    vati
    0.89
    bi
    0.88
    athi
    0.85
     ILCS
    0.84
    ttp
    0.84
    Activations Density 0.014%

    No Known Activations