© 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. 1-RES-JB
    6. 16409
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "local" appearing with high activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "local" in various contexts

    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
    xual
    -1.16
    haar
    -0.90
    issance
    -0.86
    hra
    -0.83
    SHIP
    -0.82
    uberty
    -0.81
    ppelin
    -0.80
    ACTED
    -0.78
    lihood
    -0.77
    lda
    -0.76
    POSITIVE LOGITS
     authorities
    0.85
     residents
    0.82
     local
    0.81
     grocer
    0.80
     elders
    0.79
     neighbors
    0.78
    ©¶æ
    0.78
     opio
    0.78
     corrid
    0.76
     neighbours
    0.75
    Activations Density 0.025%

    No Known Activations