© 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. 1191
    Prev
    Next
    INDEX
    Explanations

    phrases related to holding doors for strangers

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to thresholds or limits in various contexts

    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
    ahon
    -0.75
    Shin
    -0.75
     Kane
    -0.74
    Batman
    -0.72
     sickness
    -0.70
    ierrez
    -0.68
    izard
    -0.67
     Cyborg
    -0.66
    ãĥĥãĥī
    -0.65
     Shinji
    -0.64
    POSITIVE LOGITS
     Open
    2.41
    Open
    2.25
    open
    2.22
     open
    2.20
     OPEN
    2.18
     Closed
    1.90
    opens
    1.85
     openness
    1.83
     closed
    1.80
     opens
    1.76
    Activations Density 0.220%

    No Known Activations