© 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. 10-RES-JB
    11. 18592
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and instructions involving the manipulation or handling of objects

    oai_token-act-pair · gpt-3.5-turbo

    actions related to sharing, manipulating, or discussing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.80
     actionGroup
    -0.63
    These
    -0.61
    aukee
    -0.60
    raltar
    -0.60
    oult
    -0.58
    cius
    -0.58
    etsk
    -0.57
    these
    -0.55
     These
    -0.54
    POSITIVE LOGITS
     it
    1.62
     its
    1.06
    Its
    1.05
     It
    1.00
    It
    0.91
     Its
    0.91
    it
    0.89
    its
    0.85
     thereof
    0.72
    soType
    0.66
    Activations Density 1.477%

    No Known Activations