© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15796
    Prev
    Next
    INDEX
    Explanations

    mentions of lectures or academic activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to teaching or educational content

    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
    WT
    -0.63
    AAF
    -0.63
     OPEC
    -0.62
     NCT
    -0.61
     ABE
    -0.61
     Mehran
    -0.61
     Beg
    -0.61
     Connor
    -0.61
    ̶
    -0.60
    1600
    -0.59
    POSITIVE LOGITS
    lect
    1.33
    ronics
    1.10
    inel
    1.06
    urers
    1.02
    ures
    1.01
    urer
    1.01
    rics
    1.00
    rification
    0.97
    acles
    0.96
    rique
    0.96
    Activations Density 0.010%

    No Known Activations