© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5584
    Prev
    Next
    INDEX
    Explanations

    words related to physical struggle or effort, particularly related to physical pain or technological functionality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letters "wr" indicating the presence of words associated with suffering or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RON
    -0.87
    BALL
    -0.78
    ctica
    -0.72
    ãĥ´
    -0.70
     hereby
    -0.68
    HAEL
    -0.65
     issu
    -0.63
     Pav
    -0.60
     Mith
    -0.59
     bearer
    -0.59
    POSITIVE LOGITS
    inkle
    1.44
    angler
    1.16
    inging
    1.16
    iggle
    1.12
    angling
    1.11
    angle
    1.05
    ights
    1.04
    angled
    0.98
    acked
    0.97
    angles
    0.97
    Activations Density 0.013%

    No Known Activations