© 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. 2-RES-JB
    11. 23694
    Prev
    Next
    INDEX
    Explanations

    keywords related to machine and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to machines and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulet
    -0.86
    olulu
    -0.84
    ificant
    -0.77
    orb
    -0.75
    ibilities
    -0.75
    uating
    -0.74
    uds
    -0.73
    tml
    -0.73
    raints
    -0.73
    reenshots
    -0.72
    POSITIVE LOGITS
     machine
    1.01
     machines
    0.94
    Machine
    0.90
    guns
    0.87
    machine
    0.85
    gun
    0.82
     Machine
    0.82
    eers
    0.81
     guns
    0.80
     Machines
    0.79
    Activations Density 0.015%

    No Known Activations