© 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. 8-RES-JB
    11. 2601
    Prev
    Next
    INDEX
    Explanations

    instances where something is described or represented in a particular way

    oai_token-act-pair · gpt-3.5-turbo

    phrases that represent or correlate with interpretations or portrayals of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asers
    -0.72
    eor
    -0.71
    quist
    -0.70
    CHA
    -0.68
    romy
    -0.68
    ppa
    -0.67
    rone
    -0.66
    reprene
    -0.66
    ersen
    -0.65
    ctl
    -0.64
    POSITIVE LOGITS
     follows
    1.18
    pires
    1.01
    criptions
    0.94
    pired
    0.92
    phy
    0.92
     well
    0.91
    piring
    0.87
     belonging
    0.86
     opposed
    0.86
     occurring
    0.83
    Activations Density 0.156%

    No Known Activations