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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13199
    Prev
    Next
    INDEX
    Explanations

    specific locations - specifically mentioning the District of Columbia

    oai_token-act-pair · gpt-3.5-turbo

    references to specific districts, particularly the District of Columbia and other districts

    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
    cially
    -0.86
    ppo
    -0.86
    cial
    -0.85
    zza
    -0.82
    cean
    -0.81
    fty
    -0.78
    cius
    -0.78
    ndra
    -0.78
    lda
    -0.77
    ggy
    -0.76
    POSITIVE LOGITS
    rict
    0.86
    s
    0.85
     District
    0.80
     Attorney
    0.76
     Marshal
    0.74
    ing
    0.70
     attorneys
    0.64
    busters
    0.63
     Territories
    0.62
     grids
    0.62
    Activations Density 0.012%

    No Known Activations