© 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. 4-RES-JB
    11. 9739
    Prev
    Next
    INDEX
    Explanations

    locations or addresses with the word 'Road' in them

    oai_token-act-pair · gpt-3.5-turbo

    references to various roads and highways

    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
    ERAL
    -0.82
    arians
    -0.77
    irements
    -0.72
    illian
    -0.72
    enance
    -0.71
    glers
    -0.70
    arian
    -0.69
    âĸijâĸij
    -0.69
    foundland
    -0.69
    rator
    -0.68
    POSITIVE LOGITS
     Roads
    0.91
     Racer
    0.90
     Road
    0.89
    side
    0.88
    road
    0.83
    stead
    0.83
    ways
    0.82
    blocks
    0.81
    docs
    0.81
    trip
    0.79
    Activations Density 0.012%

    No Known Activations