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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17661
    Prev
    Next
    INDEX
    Explanations

    phrases where the concept of 'being fine' or 'acceptable' is expressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or adequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riber
    -0.77
    rush
    -0.73
    orical
    -0.71
     Kut
    -0.70
    iq
    -0.70
    Hack
    -0.70
    nikov
    -0.69
    raped
    -0.69
    ulhu
    -0.69
    erity
    -0.67
    POSITIVE LOGITS
     tuning
    1.02
     tuned
    0.94
     Gael
    0.83
     tune
    0.78
     fine
    0.74
    Fine
    0.74
     Haven
    0.71
    fine
    0.71
     Fine
    0.70
    baum
    0.70
    Activations Density 0.010%

    No Known Activations