© 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 EvalsExportsinterp-engineNEWAPI 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. 9143
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to acts of throwing or discarding something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the" in various contexts

    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
     suppose
    -0.71
    cé
    -0.69
    semb
    -0.68
     owing
    -0.62
     endeav
    -0.61
    replace
    -0.60
    Allows
    -0.59
    rand
    -0.59
    onse
    -0.59
    NULL
    -0.58
    POSITIVE LOGITS
     same
    1.18
     proverbial
    1.17
     entire
    1.15
     slightest
    1.11
     blame
    1.10
     hardest
    1.04
     brunt
    1.03
     remainder
    1.02
     whole
    1.01
     entirety
    0.99
    Activations Density 0.308%

    No Known Activations