© 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. 7-RES-JB
    6. 4991
    Prev
    Next
    INDEX
    Explanations

    proper nouns of locations

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and associated statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵Âł
    -0.50
    ],"
    -0.46
    ³³³
    -0.45
    ³³³³³³³³
    -0.44
    ����
    -0.42
    ³³³³
    -0.42
    ancial
    -0.42
    itent
    -0.42
     ·
    -0.41
    ³³³³³³³³³³³³³³³³
    -0.41
    POSITIVE LOGITS
     glim
    0.56
    etheless
    0.48
    asty
    0.39
    livious
    0.39
    umblr
    0.38
    ueless
    0.37
     Voltage
    0.37
     payoff
    0.37
     Canaver
    0.37
     Meow
    0.36
    Activations Density 3.884%

    No Known Activations