© 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. 7-RES-JB
    11. 2120
    Prev
    Next
    INDEX
    Explanations

    terms related to file management

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to finance and banking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.69
    urally
    -0.60
    maxwell
    -0.60
    ¶ħ
    -0.58
    mobi
    -0.58
    ãĥĥãĥī
    -0.56
    ĵĺ
    -0.55
    heast
    -0.54
    kef
    -0.53
    ãĥķãĤ©
    -0.53
    POSITIVE LOGITS
    hess
    0.62
     guiActiveUnfocused
    0.56
     pyramid
    0.55
     Sovereign
    0.55
    bearing
    0.53
    .",
    0.53
     Vector
    0.53
    grain
    0.52
     Bowen
    0.52
    bos
    0.52
    Activations Density 1.052%

    No Known Activations