© 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. 7-RES-JB
    11. 24088
    Prev
    Next
    INDEX
    Explanations

    phrases related to initiating or starting something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to initiating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emin
    -0.93
    BuyableInstoreAndOnline
    -0.68
     Sins
    -0.67
    è¯
    -0.67
    uve
    -0.66
    ORS
    -0.66
    rians
    -0.66
    umbn
    -0.65
    ILLE
    -0.65
    ancies
    -0.64
    POSITIVE LOGITS
    starter
    1.43
    starting
    1.06
    started
    1.02
    strap
    1.00
    start
    0.97
    boxing
    0.95
    tails
    0.84
    strate
    0.81
    ument
    0.80
     off
    0.78
    Activations Density 0.027%

    No Known Activations