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. 10-RES-JB
    6. 9037
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific geographical location, Palm Beach

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.75
    vous
    -0.70
    Charges
    -0.69
    hov
    -0.69
    ettings
    -0.68
    NESS
    -0.67
    red
    -0.64
    advertising
    -0.63
    rated
    -0.62
    hire
    -0.61
    POSITIVE LOGITS
    ieri
    1.18
    istry
    0.97
     Beach
    0.94
     Springs
    0.93
    endas
    0.82
    arious
    0.82
    ican
    0.81
    astic
    0.81
    ient
    0.81
    asonic
    0.80
    Activations Density 0.040%

    No Known Activations