© 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 EvalsExportsinterp-engineNEWAPI 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. 9654
    Prev
    Next
    INDEX
    Explanations

    mixed activations with a focus on various words and phrases, including names of people and locations

    oai_token-act-pair · gpt-3.5-turbo

    letter combinations and specific sequences resembling proper nouns or names

    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
     looph
    -0.75
     exting
    -0.70
    EStreamFrame
    -0.65
     subur
    -0.64
    ¥ŀ
    -0.63
     eleph
    -0.63
     millenn
    -0.63
    aditional
    -0.60
     tacit
    -0.60
    ailable
    -0.59
    POSITIVE LOGITS
    ®
    0.68
    phia
    0.68
    cious
    0.66
    ãĤ£
    0.66
    abilia
    0.64
    ronics
    0.64
    eni
    0.63
    ippi
    0.62
    illus
    0.61
    _-
    0.60
    Activations Density 0.698%

    No Known Activations