© 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. 4-RES-JB
    11. 7155
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences mentioning conformity or alignment with standards or expectations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in line."

    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
    CVE
    -0.93
    soever
    -0.80
    ueller
    -0.76
    ilt
    -0.76
    rw
    -0.75
    ONSORED
    -0.70
    ravel
    -0.69
    ramid
    -0.68
    uckle
    -0.67
    Interstitial
    -0.67
    POSITIVE LOGITS
    backer
    0.88
     Lines
    0.75
    naires
    0.70
     line
    0.69
     lines
    0.68
     vein
    0.67
    lines
    0.66
    book
    0.65
    line
    0.62
    aments
    0.61
    Activations Density 0.018%

    No Known Activations