Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23589
    Prev
    Next
    INDEX
    Explanations

    locations or places where events occurred

    oai_token-act-pair · gpt-3.5-turbo

    locations mentioned in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hack
    -0.63
    ifest
    -0.62
    iva
    -0.62
    yp
    -0.61
    apult
    -0.61
    ynasty
    -0.61
    Grade
    -0.60
    pac
    -0.60
     incent
    -0.59
    tty
    -0.59
    POSITIVE LOGITS
    upon
    1.92
     they
    1.13
    soever
    1.12
     he
    1.03
     she
    0.92
    abouts
    0.89
     temperatures
    0.81
     there
    0.79
     it
    0.76
     tensions
    0.75
    Activations Density 0.081%

    No Known Activations