© 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. 19319
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of offering or providing something helpful or beneficial to others

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the prefix "aff" indicating various forms of the word "affect" or related terms

    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
    DragonMagazine
    -0.78
    ²¾
    -0.77
    çķ
    -0.71
    BOX
    -0.71
     pus
    -0.67
    SpaceEngineers
    -0.67
    UES
    -0.64
     cleaners
    -0.64
     Weir
    -0.64
     Wonderland
    -0.64
    POSITIVE LOGITS
    luence
    1.27
    irming
    1.26
    liction
    1.21
    ront
    1.16
    ixed
    1.11
    idav
    1.10
    irms
    1.10
    irm
    1.08
    irmation
    1.08
    irmed
    1.07
    Activations Density 0.025%

    No Known Activations