© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 591
    Prev
    Next
    INDEX
    Explanations

    words containing the sequence "ple"

    oai_token-act-pair · gpt-4-turbo

    phrases related to things decreasing or diminishing

    oai_token-act-pair · gpt-3.5-turbo

    words related to pleasing or delightful experiences

    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
    è¦ļéĨĴ
    -0.80
    Downloadha
    -0.80
    Reviewer
    -0.74
    ahime
    -0.72
    DERR
    -0.69
    uador
    -0.69
     Moroc
    -0.66
    rolet
    -0.66
    dayName
    -0.63
    é¾
    -0.62
    POSITIVE LOGITS
    ple
    1.28
    ples
    0.90
    plet
    0.86
    ply
    0.84
    mented
    0.84
    xt
    0.77
    teness
    0.77
    veyard
    0.76
    asure
    0.75
    lee
    0.74
    Activations Density 0.009%

    No Known Activations