© 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. 7-RES-JB
    11. 9172
    Prev
    Next
    INDEX
    Explanations

    measurements or distances

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain significant punctuation marks or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prosperity
    -0.69
     persever
    -0.63
    ŃĶ
    -0.62
     affili
    -0.62
    reprene
    -0.62
    itatively
    -0.61
     accol
    -0.60
    conom
    -0.60
     prosperous
    -0.59
    riers
    -0.59
    POSITIVE LOGITS
     Previously
    1.14
    instead
    1.13
    Previously
    1.01
     Whereas
    0.93
     Normally
    0.92
    rather
    0.85
     Presumably
    0.84
     Instead
    0.82
    Instead
    0.81
     Meaning
    0.80
    Activations Density 1.108%

    No Known Activations