© 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. 3-RES-JB
    11. 24146
    Prev
    Next
    INDEX
    Explanations

    explicitly marked sections with three asterisks '***'

    oai_token-act-pair · gpt-3.5-turbo

    repeated or emphasized symbols, particularly asterisks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.81
     srf
    -0.80
    uces
    -0.79
     exting
    -0.75
    vation
    -0.75
    oded
    -0.75
    odes
    -0.74
    anyl
    -0.74
    ŃĶ
    -0.72
    ugal
    -0.72
    POSITIVE LOGITS
    ***
    0.84
    =-=-
    0.81
     ***
    0.81
    !/
    0.79
    TOP
    0.78
    IER
    0.78
    HAEL
    0.74
    hole
    0.74
    **
    0.72
    ~~~~
    0.72
    Activations Density 0.010%

    No Known Activations