© 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. 1-RES-JB
    11. 24328
    Prev
    Next
    INDEX
    Explanations

    specific initialization strings that often appear in code

    oai_token-act-pair · gpt-3.5-turbo

    programming concepts related to initialization in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.75
     Emin
    -0.65
    QL
    -0.62
     drinkers
    -0.62
     abusers
    -0.62
     knees
    -0.60
    PH
    -0.60
    aws
    -0.60
    Temperature
    -0.59
    hair
    -0.58
    POSITIVE LOGITS
     Init
    1.17
    init
    1.03
    iation
    1.01
    itial
    0.96
     init
    0.91
    itially
    0.91
    rek
    0.82
    ATION
    0.79
    isation
    0.79
    itus
    0.79
    Activations Density 0.014%

    No Known Activations