© 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. 3-RES-JB
    11. 23125
    Prev
    Next
    INDEX
    Explanations

    verbally and visually strong action words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slash" and its variations, indicating reductions or cuts in various contexts

    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
    gran
    -0.79
    Pa
    -0.74
     Nou
    -0.70
    Liber
    -0.70
    Pers
    -0.69
    aque
    -0.67
    Lost
    -0.67
    cause
    -0.67
    ________________________
    -0.65
    haar
    -0.65
    POSITIVE LOGITS
     slash
    1.13
     slashed
    1.03
    ashtra
    0.98
     wrists
    0.96
    cliffe
    0.88
     slashing
    0.86
     slicing
    0.85
    lasses
    0.83
     Slash
    0.80
     chop
    0.76
    Activations Density 0.008%

    No Known Activations