© 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. 7-RES-JB
    6. 21372
    Prev
    Next
    INDEX
    Explanations

    terms related to urban areas or urban development

    oai_token-act-pair · gpt-3.5-turbo

    mentions of urban-related topics or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iris
    -0.84
    utations
    -0.81
    ãĤ´ãĥ³
    -0.78
    sembly
    -0.77
    xon
    -0.75
    UNE
    -0.74
    utes
    -0.73
    UTERS
    -0.72
    utherland
    -0.72
    othal
    -0.71
    POSITIVE LOGITS
     Dictionary
    0.97
     Decay
    0.95
    ization
    0.87
    ized
    0.86
     Meyer
    0.78
    icity
    0.77
     Warfare
    0.76
    Tur
    0.76
    izing
    0.75
     Moving
    0.74
    Activations Density 0.018%

    No Known Activations