© 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. 8-RES-JB
    11. 19333
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to teaching or instructing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to education and training initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tar
    -0.68
    bid
    -0.67
    /
    -0.66
    ftime
    -0.65
    :-
    -0.61
    ----------
    -0.61
    areth
    -0.59
     owing
    -0.59
    provided
    -0.58
    lived
    -0.58
    POSITIVE LOGITS
     entire
    1.13
     populace
    0.96
     fledgling
    0.96
     younger
    0.92
     unsuspecting
    0.92
     nascent
    0.91
     young
    0.90
     gull
    0.88
    selves
    0.86
     wearer
    0.86
    Activations Density 0.233%

    No Known Activations