© 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. 0-RES-JB
    11. 13673
    Prev
    Next
    INDEX
    Explanations

    instances of the word "abs"

    oai_token-act-pair · gpt-3.5-turbo

    the word "abs" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warner
    -0.64
     gol
    -0.61
     order
    -0.61
     song
    -0.61
     Sandy
    -0.60
     Glen
    -0.60
     Lionel
    -0.60
     Lady
    -0.59
     Byron
    -0.59
     Lover
    -0.58
    POSITIVE LOGITS
    abs
    4.68
    ab
    1.70
    Abs
    1.54
    abb
    1.29
     Abs
    1.23
    abi
    1.15
    AB
    1.09
    aber
    1.08
    obs
    1.08
    ashes
    1.07
    Activations Density 0.008%

    No Known Activations