© 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. 2-RES-JB
    11. 19739
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "shop"

    oai_token-act-pair · gpt-3.5-turbo

    references to "hop" as a key term, likely in the context of music or beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.85
     behold
    -0.67
     bruising
    -0.66
    anguage
    -0.61
     withd
    -0.60
     IMAGES
    -0.59
    âĶĢâĶĢ
    -0.59
    INE
    -0.57
    isle
    -0.57
    evil
    -0.56
    POSITIVE LOGITS
    efully
    1.46
    eful
    1.38
    hop
    1.36
    Hop
    1.09
    eless
    1.07
    achu
    0.92
    daq
    0.91
    esy
    0.88
    hops
    0.84
     Hop
    0.84
    Activations Density 0.007%

    No Known Activations