© 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. 4374
    Prev
    Next
    INDEX
    Explanations

    text related to locations like "San Francisco", "San Diego", and "San Antonio"

    oai_token-act-pair · gpt-3.5-turbo

    special tokens or markers that indicate the beginning or end of segments, as well as references to "San" 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
    ives
    -0.83
    urned
    -0.77
     Nebula
    -0.69
    depend
    -0.67
    dash
    -0.67
    uyomi
    -0.66
    urn
    -0.65
    llor
    -0.65
    llers
    -0.64
    ym
    -0.62
    POSITIVE LOGITS
    ctuary
    1.18
    ction
    0.92
    atural
    0.88
    ctions
    0.81
    SAN
    0.81
    OTHER
    0.80
     ANGEL
    0.80
     Alto
    0.79
    folio
    0.78
    folios
    0.78
    Activations Density 0.021%

    No Known Activations