© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 23587
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations or entities, particularly islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ents
    -0.72
    iously
    -0.68
    SG
    -0.68
    ital
    -0.67
    1959
    -0.65
    elaide
    -0.65
    lished
    -0.65
     [+
    -0.65
    ENTS
    -0.63
    ellar
    -0.63
    POSITIVE LOGITS
     Isle
    1.37
     Isles
    1.01
     Royale
    0.96
     Enix
    0.81
    ortment
    0.80
    sburg
    0.76
    mania
    0.75
    wright
    0.73
    pload
    0.73
    ignt
    0.72
    Activations Density 0.013%

    No Known Activations