© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10876
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographical locations, particularly canyons and national parks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of canyons and related geographical features

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

    No Comments

    Negative Logits
    encers
    -0.85
    encer
    -0.85
    enced
    -0.77
    ively
    -0.74
    iveness
    -0.73
     advoc
    -0.71
    iencies
    -0.70
    ÑĮ
    -0.69
    ortun
    -0.67
    ews
    -0.67
    POSITIVE LOGITS
     Canyon
    1.03
     Springs
    0.94
     canyon
    0.94
     Rapids
    0.87
    lake
    0.83
     Dwell
    0.82
    lands
    0.82
     Mesa
    0.78
    lace
    0.76
     Rim
    0.75
    Activations Density 0.015%

    No Known Activations