© 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. 9-RES-JB
    11. 1954
    Prev
    Next
    INDEX
    Explanations

    words related to reduction or decrease

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reduced" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bet
    -0.61
    ervative
    -0.61
    finished
    -0.60
     Remastered
    -0.60
    ipe
    -0.59
    lé
    -0.59
    atom
    -0.58
    thing
    -0.57
     Sina
    -0.56
    aint
    -0.56
    POSITIVE LOGITS
     inhib
    0.85
    icides
    0.79
    ahime
    0.78
     effectiveness
    0.76
     workload
    0.75
     visibility
    0.75
     thickness
    0.75
     sidx
    0.74
    xual
    0.72
     severity
    0.70
    Activations Density 0.074%

    No Known Activations