© 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. 20523
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of starting or commencing something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of beginnings or origins

    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
    rored
    -0.79
    anamo
    -0.74
    resa
    -0.71
    regon
    -0.70
    ellow
    -0.69
    avorite
    -0.68
    rosso
    -0.66
    ilings
    -0.65
    eeper
    -0.64
    rh
    -0.63
    POSITIVE LOGITS
     onwards
    1.19
     onward
    1.02
     standpoint
    1.00
     inception
    0.83
     perspective
    0.77
     point
    0.72
     viewpoint
    0.71
     outset
    0.66
     !!
    0.64
    .�
    0.63
    Activations Density 0.108%

    No Known Activations