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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 23392
    Prev
    Next
    INDEX
    Explanations

    the city name "San Francisco"

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hire
    -0.88
     Hound
    -0.69
    vet
    -0.68
     hire
    -0.63
     minus
    -0.62
     pocket
    -0.62
     Von
    -0.62
     Titan
    -0.61
     Iron
    -0.61
     Fedora
    -0.61
    POSITIVE LOGITS
    ANC
    4.71
    ANCE
    2.83
    ances
    2.10
    anc
    1.80
    anced
    1.76
    ancers
    1.71
    ancing
    1.69
    ance
    1.69
    ANT
    1.65
    ancy
    1.55
    Activations Density 0.008%

    No Known Activations