© 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. 0-RES-JB
    6. 16531
    Prev
    Next
    INDEX
    Explanations

    locations or terms related to transportation or specific places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elephant
    -0.64
     Dalai
    -0.64
     nihil
    -0.62
     inh
    -0.62
     uncertainties
    -0.60
     Shining
    -0.60
     ka
    -0.58
     syll
    -0.57
     Fellow
    -0.57
     thri
    -0.57
    POSITIVE LOGITS
    port
    4.64
    ports
    3.04
    PORT
    2.39
    Port
    2.23
    porting
    2.21
    ported
    1.71
    portation
    1.71
     Port
    1.46
     port
    1.41
    porter
    1.39
    Activations Density 0.010%

    No Known Activations