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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 15858
    Prev
    Next
    INDEX
    Explanations

    directional location terms, particularly focusing on the aspects of east and west

    oai_token-act-pair · gpt-3.5-turbo

    directional geographic descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioned
    -0.74
     delinquent
    -0.68
    thood
    -0.66
     guiActiveUn
    -0.66
    Score
    -0.65
    pload
    -0.65
    elist
    -0.62
    ello
    -0.60
     expire
    -0.60
     showc
    -0.58
    POSITIVE LOGITS
    west
    1.02
    east
    0.99
     Territories
    0.94
    wards
    0.91
     Queensland
    0.84
    western
    0.83
    outheast
    0.82
     latitude
    0.82
    lake
    0.78
     corner
    0.73
    Activations Density 0.070%

    No Known Activations