© 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. 23500
    Prev
    Next
    INDEX
    Explanations

    prepositions in German

    oai_token-act-pair · gpt-3.5-turbo

    the word "an" in various contexts

    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
    BAT
    -0.74
    çĭ
    -0.65
    dylib
    -0.63
     branches
    -0.60
     Brach
    -0.60
     delet
    -0.58
    ãĤ©
    -0.58
     Peg
    -0.57
     Writ
    -0.57
     Paste
    -0.55
    POSITIVE LOGITS
    ointed
    1.18
    cients
    1.15
    iversary
    1.14
    abolic
    1.12
    agram
    1.11
    ointment
    1.08
    oint
    1.08
    notation
    0.99
    onymous
    0.97
    onym
    0.97
    Activations Density 0.131%

    No Known Activations