© 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 EvalsExportsinterp-engineNEWAPI 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. 17897
    Prev
    Next
    INDEX
    Explanations

    terms related to questions or prompts

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various contexts

    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
    è¦ļéĨĴ
    -0.77
    è£
    -0.76
    ãģĮ
    -0.75
     ABE
    -0.74
    IOR
    -0.72
    ãĤ¨ãĥ«
    -0.71
     credits
    -0.68
     fins
    -0.68
    ¥µ
    -0.67
     guiActiveUnfocused
    -0.67
    POSITIVE LOGITS
    olated
    1.11
    olate
    1.01
    ync
    0.97
    olation
    0.92
    terness
    0.91
    acan
    0.83
    nt
    0.81
    earch
    0.80
    senal
    0.79
    Ps
    0.79
    Activations Density 0.012%

    No Known Activations