© 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. 20553
    Prev
    Next
    INDEX
    Explanations

    words related to opinions or positions on certain topics

    oai_token-act-pair · gpt-3.5-turbo

    references to opinions or positions on various issues

    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
    NetMessage
    -0.79
    Interstitial
    -0.74
    cing
    -0.71
    ined
    -0.68
    athan
    -0.67
    esters
    -0.66
    duct
    -0.66
    STON
    -0.64
    isle
    -0.64
    cible
    -0.64
    POSITIVE LOGITS
     stance
    1.31
     stances
    1.19
     positions
    0.90
     toward
    0.89
     towards
    0.86
     position
    0.85
    yip
    0.83
     posture
    0.80
     views
    0.79
     bent
    0.76
    Activations Density 0.016%

    No Known Activations