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. 3168
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly areas such as Queens and the Bronx

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the boroughs of Queens and the Bronx

    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
    aneous
    -0.81
    aneously
    -0.70
    Äĩ
    -0.69
    herer
    -0.67
    inen
    -0.66
    ischer
    -0.65
    akable
    -0.63
    angible
    -0.63
    letcher
    -0.62
    ained
    -0.61
    POSITIVE LOGITS
    boro
    1.01
    borough
    0.93
     Borough
    0.87
    folk
    0.86
    hall
    0.83
    bury
    0.83
    walk
    0.80
    port
    0.80
     Queens
    0.80
    uits
    0.80
    Activations Density 0.009%

    No Known Activations