© 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. 10-RES-JB
    11. 2914
    Prev
    Next
    INDEX
    Explanations

    phrases related to a requirement, necessity, or obligation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.72
     Onion
    -0.63
     eyeing
    -0.63
     pressing
    -0.57
    mort
    -0.57
     rash
    -0.56
     mir
    -0.56
    ahime
    -0.55
     prest
    -0.55
    SHIP
    -0.54
    POSITIVE LOGITS
    wered
    1.03
     happen
    1.02
     be
    1.01
     occur
    0.99
     suffice
    0.97
     belong
    0.90
     originate
    0.89
     involve
    0.87
     preced
    0.85
     exist
    0.83
    Activations Density 0.068%

    No Known Activations