© 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. 2-RES-JB
    6. 17803
    Prev
    Next
    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --+
    -0.84
    thood
    -0.78
    wagen
    -0.74
    bs
    -0.71
    andr
    -0.71
    ass
    -0.71
    wcsstore
    -0.69
    nit
    -0.68
    Ign
    -0.68
    oly
    -0.68
    POSITIVE LOGITS
     southwest
    0.81
     southeast
    0.80
     Corridor
    0.73
     northwest
    0.73
     Regional
    0.72
    使
    0.71
     corner
    0.70
     bloc
    0.69
     northeast
    0.68
     Kazakhstan
    0.68
    Activations Density 0.010%

    No Known Activations