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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 8654
    Prev
    Next
    INDEX
    Explanations

    major cities where conferences or events are being held

    oai_token-act-pair · gpt-3.5-turbo

    specific locations or cities mentioned in the text

    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
    redo
    -0.65
    ramid
    -0.64
    inyl
    -0.61
    merce
    -0.61
    omorph
    -0.59
     complexion
    -0.59
    venge
    -0.58
     adv
    -0.57
    ategories
    -0.57
    Ps
    -0.56
    POSITIVE LOGITS
     Harbor
    0.88
     Bay
    0.87
     Meadows
    0.85
     Heights
    0.83
     suburb
    0.81
     Gardens
    0.80
     harbor
    0.79
     County
    0.79
     airspace
    0.78
     suburbs
    0.77
    Activations Density 0.222%

    No Known Activations