© 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. 4-RES-JB
    11. 7543
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or speculation

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

    No Comments

    Negative Logits
     corrid
    -0.56
     pend
    -0.52
     referen
    -0.51
     Rober
    -0.51
    ueless
    -0.50
     millenn
    -0.50
    ificant
    -0.49
    Higher
    -0.49
     conclud
    -0.49
    Compar
    -0.48
    POSITIVE LOGITS
    Ĥİ
    0.58
    SourceFile
    0.57
    bra
    0.56
     Uncharted
    0.52
    isons
    0.51
    TOR
    0.51
    tesy
    0.51
    rawdownloadcloneembedreportprint
    0.50
    Vert
    0.50
    hirt
    0.49
    Activations Density 1.215%

    No Known Activations