© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    6. 4405
    Prev
    Next
    INDEX
    Explanations

    names of locations or people starting with 'Le'

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that are associated with geographical locations or urban areas

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

    No Comments

    Negative Logits
    »Ĵ
    -0.89
    ĨĴ
    -0.84
    é¾įå¥ij士
    -0.75
    ãģ¦
    -0.72
    Effective
    -0.68
     Charleston
    -0.67
    GMT
    -0.67
     tremend
    -0.66
    ²¾
    -0.65
    REDACTED
    -0.65
    POSITIVE LOGITS
    iste
    0.85
    velt
    0.79
    orce
    0.78
    heed
    0.77
    oche
    0.74
     Observatory
    0.72
    anium
    0.72
    andro
    0.71
    frog
    0.71
    onge
    0.71
    Activations Density 0.077%

    No Known Activations