© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 5771
    Prev
    Next
    INDEX
    Explanations

    words related to plans, explanations, or relations between entities

    oai_token-act-pair · gpt-3.5-turbo

    the presence of special or non-standard characters, particularly the end-of-text token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.65
    âĢķ
    -0.64
     respectively
    -0.63
     â̦"
    -0.62
    ,...
    -0.62
     cig
    -0.61
     cough
    -0.61
     fair
    -0.60
    Bey
    -0.60
     tremend
    -0.59
    POSITIVE LOGITS
    ations
    1.05
    itably
    1.03
    itionally
    1.02
    hetically
    1.01
    ologists
    1.00
    orically
    0.99
    ating
    0.97
    inarily
    0.97
    ements
    0.96
    ational
    0.96
    Activations Density 0.196%

    No Known Activations