© 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. 7-RES-JB
    11. 9340
    Prev
    Next
    INDEX
    Explanations

    specific names or entities, like "Paul J. Watson"

    oai_token-act-pair · gpt-3.5-turbo

    specific references to individuals or names, particularly notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.59
    anyon
    -0.56
    ucl
    -0.56
    icket
    -0.54
    rencies
    -0.54
    £ı
    -0.53
    etheless
    -0.53
    ativity
    -0.53
    UTERS
    -0.52
    ologies
    -0.52
    POSITIVE LOGITS
    istan
    0.65
    assi
    0.52
    zing
    0.50
    lov
    0.49
    fill
    0.49
    region
    0.48
    255
    0.46
    inic
    0.46
     Idlib
    0.46
    ulu
    0.46
    Activations Density 0.959%

    No Known Activations