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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6667
    Prev
    Next
    INDEX
    Explanations

    names of cities, with a particular focus on Seattle

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Seattle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocr
    -0.76
    ktop
    -0.73
    arial
    -0.72
    Topic
    -0.72
    ����
    -0.70
    onies
    -0.69
     vit
    -0.68
    eline
    -0.67
    ========
    -0.66
    ombs
    -0.66
    POSITIVE LOGITS
     Sounders
    1.41
     Seahawks
    1.21
     Mariners
    1.21
     Tacoma
    1.06
    Seattle
    1.02
    ites
    0.96
     Seattle
    0.92
     Reign
    0.89
     Seah
    0.84
     Rapids
    0.82
    Activations Density 0.014%

    No Known Activations