© 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. 14572
    Prev
    Next
    INDEX
    Explanations

    words related to flexibility or being flexible in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flexible."

    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
    ICAN
    -0.80
    bey
    -0.77
    roy
    -0.71
     Famous
    -0.70
     Bam
    -0.69
    tha
    -0.67
    FORE
    -0.66
    ifice
    -0.66
    ilet
    -0.66
    orig
    -0.66
    POSITIVE LOGITS
    atile
    0.97
    ible
    0.96
    atility
    0.96
    ibilities
    0.91
     flexibility
    0.89
    ibility
    0.85
    ibly
    0.84
     minded
    0.82
    ensical
    0.79
     flex
    0.78
    Activations Density 0.018%

    No Known Activations