© 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. 0-RES-JB
    11. 1093
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Indiana

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Indiana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     nar
    -0.73
    uploads
    -0.73
    assad
    -0.72
    âĶĢâĶĢ
    -0.72
    Ñı
    -0.69
     clan
    -0.68
    és
    -0.67
    ange
    -0.67
    Ts
    -0.67
     DAC
    -0.66
    POSITIVE LOGITS
     Indiana
    3.70
    Indiana
    3.56
     Indianapolis
    2.22
     Pacers
    1.90
     Ohio
    1.89
     Illinois
    1.88
     Kentucky
    1.87
     Purdue
    1.85
     Indy
    1.79
     Iowa
    1.77
    Activations Density 0.021%

    No Known Activations