© 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. 2-RES-JB
    11. 15515
    Prev
    Next
    INDEX
    Explanations

    words related to being widely and commonly found or present

    oai_token-act-pair · gpt-3.5-turbo

    terms related to widespread presence or commonality

    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
    izons
    -0.76
    Merit
    -0.71
    thur
    -0.69
    ttle
    -0.67
    WAR
    -0.67
    ander
    -0.65
    owitz
    -0.65
    stri
    -0.64
    FK
    -0.64
    hner
    -0.64
    POSITIVE LOGITS
     ubiquitous
    1.01
     ubiqu
    0.94
    resent
    0.78
    icity
    0.78
    entimes
    0.72
    ãĤ¢ãĥ«
    0.71
    wealth
    0.70
     omnip
    0.69
    etheless
    0.69
     presence
    0.69
    Activations Density 0.014%

    No Known Activations