© 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. 1-RES-JB
    11. 2683
    Prev
    Next
    INDEX
    Explanations

    locations and abbreviations of states in the United States

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or codes for U.S. states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.86
    ãĥ¼ãĥ³
    -0.86
    tainment
    -0.84
    framework
    -0.84
    ptives
    -0.83
    ãĤ©
    -0.79
    ãĥĺ
    -0.79
    osterone
    -0.78
    ãĥ©
    -0.77
    ãĥĵ
    -0.76
    POSITIVE LOGITS
    UX
    0.80
    UGE
    0.79
    GA
    0.77
     VT
    0.76
    VD
    0.74
    LC
    0.74
    TP
    0.73
    VT
    0.72
    TF
    0.71
     slit
    0.70
    Activations Density 0.012%

    No Known Activations