© 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. 24480
    Prev
    Next
    INDEX
    Explanations

    words related to administrative and registration activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to administration and regulatory contexts

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.77
     Grip
    -0.76
     grip
    -0.71
     phosphate
    -0.68
    mington
    -0.67
    ipple
    -0.67
    ITE
    -0.67
    terday
    -0.64
    utherford
    -0.64
    knife
    -0.62
    POSITIVE LOGITS
    rator
    1.54
    rative
    1.40
    rators
    1.31
    rix
    1.29
    ration
    1.28
    rations
    1.26
    rals
    1.22
    rous
    1.22
    ri
    1.19
    rique
    1.19
    Activations Density 0.032%

    No Known Activations