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. 3-RES-JB
    6. 18975
    Prev
    Next
    INDEX
    Explanations

    references to the country of Trinidad & Tobago

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity, particularly "Tobago."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.74
     Gamergate
    -0.68
    âĸ¬âĸ¬
    -0.66
     polarized
    -0.66
     actionGroup
    -0.65
     unconscious
    -0.65
    CLUD
    -0.64
    FORMATION
    -0.62
    Ĥİ
    -0.62
     laureate
    -0.62
    POSITIVE LOGITS
     Tob
    1.21
    arez
    1.01
    olit
    0.87
    oba
    0.86
    rien
    0.86
    ule
    0.85
    acco
    0.85
    ares
    0.85
    oro
    0.84
    idan
    0.83
    Activations Density 0.017%

    No Known Activations