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. 4-RES-JB
    6. 21525
    Prev
    Next
    INDEX
    Explanations

    words related to the location "Harlem."

    oai_token-act-pair · gpt-3.5-turbo

    references to Harlem and its associated notable figures or entities

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

    No Comments

    Negative Logits
    ertodd
    -0.75
    ansas
    -0.71
    es
    -0.69
     cheat
    -0.65
     Shelley
    -0.64
    racuse
    -0.61
    eus
    -0.61
    ITH
    -0.60
     desktop
    -0.60
     Helena
    -0.59
    POSITIVE LOGITS
    aji
    0.85
    arious
    0.74
     Barcl
    0.72
    owship
    0.71
    OVER
    0.70
    oles
    0.70
    affer
    0.69
     Mahar
    0.68
    oir
    0.68
     Reconstruction
    0.67
    Activations Density 0.022%

    No Known Activations