© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24156
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "considered."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of something being widely regarded or evaluated in a certain way

    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
    inas
    -0.74
    LET
    -0.68
    ierre
    -0.67
    arling
    -0.67
    essions
    -0.65
    ciating
    -0.63
    ogram
    -0.63
    idences
    -0.62
    eries
    -0.62
    ranging
    -0.61
    POSITIVE LOGITS
     taboo
    0.97
     ausp
    0.96
     unworthy
    0.94
     unlucky
    0.91
     undesirable
    0.91
     advisable
    0.89
     indispensable
    0.89
     desirable
    0.89
     worthy
    0.87
     preferable
    0.86
    Activations Density 0.075%

    No Known Activations