© 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. 4880
    Prev
    Next
    INDEX
    Explanations

    the name "Lan" with different numerical values reflecting the strength of the match

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or entity

    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
    IBLE
    -0.70
     Continued
    -0.66
    é¾įå¥ij士
    -0.65
    ĻĤ
    -0.65
    submit
    -0.62
    ORY
    -0.61
    PsyNetMessage
    -0.60
    ENTION
    -0.60
    graded
    -0.60
    ctl
    -0.59
    POSITIVE LOGITS
     Lan
    1.18
    unci
    1.00
    eway
    0.97
    igans
    0.93
    agall
    0.91
    olin
    0.90
    ifest
    0.89
    cil
    0.89
    emark
    0.89
    ju
    0.88
    Activations Density 0.007%

    No Known Activations