© 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. 6-RES-JB
    11. 15474
    Prev
    Next
    INDEX
    Explanations

    the surname "Ridgway."

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the letter 'g' in various contexts

    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
     compr
    -0.75
    ĸļ
    -0.71
     psychiat
    -0.71
     scrut
    -0.67
     mosqu
    -0.64
     concess
    -0.64
     derail
    -0.62
     refere
    -0.60
    oÄŁ
    -0.60
     challeng
    -0.59
    POSITIVE LOGITS
    uild
    1.28
    ossip
    1.15
    reens
    1.12
    raphics
    1.12
    raham
    1.08
    raphic
    1.08
    hetto
    1.07
    endered
    1.04
    rosso
    1.03
    ospel
    1.03
    Activations Density 0.044%

    No Known Activations