© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 9939
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being spread or covering a wide area

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the phrase "across the" followed by various contexts, indicating a focus on geographical or widespread implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icho
    -0.69
     Pastor
    -0.68
    jac
    -0.63
    ISON
    -0.61
    OFF
    -0.59
    CVE
    -0.59
    Anonymous
    -0.59
    trak
    -0.59
    nery
    -0.58
    witch
    -0.58
    POSITIVE LOGITS
     spectrum
    1.04
     globe
    1.03
     entire
    0.98
     aisle
    0.98
     country
    0.96
     entirety
    0.94
     breadth
    0.91
     whole
    0.87
     nation
    0.86
     board
    0.86
    Activations Density 0.060%

    No Known Activations