© 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. 1-RES-JB
    11. 14547
    Prev
    Next
    INDEX
    Explanations

    the word *anes*

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of compound or material

    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
    ORY
    -0.78
    è¦ļéĨĴ
    -0.75
    ECH
    -0.68
    MER
    -0.68
    DOC
    -0.68
     HIT
    -0.65
     WATCHED
    -0.61
    è¯
    -0.61
    ARGET
    -0.59
     Hoover
    -0.58
    POSITIVE LOGITS
    anes
    1.06
    layer
    0.91
    perm
    0.88
    aukee
    0.85
    elaide
    0.84
    nery
    0.83
    ryu
    0.83
    cia
    0.82
    ahime
    0.82
    ysc
    0.82
    Activations Density 0.007%

    No Known Activations