© 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. 11-RES-JB
    11. 90
    Prev
    Next
    INDEX
    Explanations

    phrases with the letter "L" and a specific activation value

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the letter "L"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleasure
    -0.71
     ringing
    -0.67
     subsistence
    -0.66
     Prohibition
    -0.66
     texting
    -0.64
     residue
    -0.64
     notification
    -0.64
     periodic
    -0.63
     notifications
    -0.63
     mitigating
    -0.62
    POSITIVE LOGITS
    arkin
    1.35
    utz
    1.29
    atham
    1.26
    aughlin
    1.24
    acey
    1.21
    oyd
    1.20
    ifestyle
    1.16
    icht
    1.16
    ocker
    1.15
    oom
    1.15
    Activations Density 0.032%

    No Known Activations