© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4673
    Prev
    Next
    INDEX
    Explanations

    comparative words indicating a lower degree or status

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inferiority or lower status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DK
    -0.74
    =-=-=-=-=-=-=-=-
    -0.74
    MM
    -0.68
    Closure
    -0.66
    raltar
    -0.66
    VR
    -0.66
    Machine
    -0.66
    ebus
    -0.65
    HER
    -0.65
    alys
    -0.65
    POSITIVE LOGITS
     than
    0.98
    etheless
    0.90
     lesser
    0.90
     sized
    0.85
     minded
    0.80
    than
    0.79
     proport
    0.73
     fractions
    0.72
     halves
    0.71
     "$:/
    0.69
    Activations Density 0.006%

    No Known Activations