© 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. 11315
    Prev
    Next
    INDEX
    Explanations

    commands or instructions indicated by the word "if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and scenarios

    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
    rolet
    -0.74
    ictionary
    -0.70
    ocker
    -0.69
    elman
    -0.65
    oho
    -0.65
    ructose
    -0.65
    roma
    -0.63
    âĵĺ
    -0.63
    vertisement
    -0.62
    ruary
    -0.60
    POSITIVE LOGITS
     necessary
    1.68
     needed
    1.56
     possible
    1.52
     practicable
    1.32
     feasible
    1.30
     warranted
    1.30
     desired
    1.23
    needed
    1.21
     appropriate
    1.20
    necessary
    1.18
    Activations Density 0.191%

    No Known Activations