© 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. 21566
    Prev
    Next
    INDEX
    Explanations

    phrases related to assessing actions or behaviors against some standard or benchmark

    oai_token-act-pair · gpt-3.5-turbo

    expressions of realization or unexpected outcomes

    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
    abal
    -0.52
    atar
    -0.51
    tnc
    -0.49
    "}],"
    -0.49
    appropriately
    -0.46
    antes
    -0.45
    clad
    -0.45
    alist
    -0.44
    oided
    -0.44
    eree
    -0.44
    POSITIVE LOGITS
    nces
    0.60
     however
    0.53
     moreover
    0.51
     furthermore
    0.50
    theless
    0.50
    DATA
    0.48
    etheless
    0.48
     meanwhile
    0.48
     WATCHED
    0.46
    nce
    0.45
    Activations Density 4.735%

    No Known Activations