© 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. 7568
    Prev
    Next
    INDEX
    Explanations

    words related to perfection or suitability

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sense of suitability or perfection

    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
    ngth
    -0.91
    leness
    -0.89
    rir
    -0.76
    Downloadha
    -0.75
    clerosis
    -0.74
    important
    -0.71
    ARDS
    -0.71
    raint
    -0.71
    popular
    -0.69
    hs
    -0.69
    POSITIVE LOGITS
     target
    1.30
     candidate
    1.22
     backdrop
    1.19
     scapego
    1.16
     venue
    1.16
     destination
    1.13
     vantage
    1.06
     place
    1.05
     habitat
    1.05
     choice
    1.04
    Activations Density 0.180%

    No Known Activations