© 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. 2-RES-JB
    11. 10455
    Prev
    Next
    INDEX
    Explanations

    words related to a specific direction, often indicating a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nai
    -0.76
    LU
    -0.75
    bians
    -0.74
    tein
    -0.73
    TL
    -0.70
    TED
    -0.69
    VA
    -0.66
    zb
    -0.66
    enos
    -0.66
    Prof
    -0.65
    POSITIVE LOGITS
     direction
    1.31
     directions
    1.22
    direction
    0.86
    finding
    0.85
    eering
    0.82
    naire
    0.77
     Direction
    0.76
    arity
    0.74
     alignment
    0.73
     orientation
    0.73
    Activations Density 0.010%

    No Known Activations