© 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. 5023
    Prev
    Next
    INDEX
    Explanations

    words related to language, especially verbs indicating action and concepts related to language

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to language development and its dynamic nature

    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
    iens
    -0.67
     Stir
    -0.63
    ovember
    -0.63
    @
    -0.62
     âĵĺ
    -0.62
    isode
    -0.60
     Liter
    -0.59
    iasis
    -0.59
    ourn
    -0.58
    inburgh
    -0.57
    POSITIVE LOGITS
     outweigh
    0.71
     inherently
    0.68
     anyway
    0.68
     poorly
    0.68
     anyways
    0.67
     crappy
    0.65
     tariff
    0.65
     finite
    0.64
     subsidized
    0.64
     unreliable
    0.64
    Activations Density 1.760%

    No Known Activations