© 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. 2-RES-JB
    11. 12504
    Prev
    Next
    INDEX
    Explanations

    references to illegal activities or contraband

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "abandon" and related themes of abandonment

    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
     retiring
    -0.71
     gobl
    -0.69
    soDeliveryDate
    -0.68
    verson
    -0.66
     slope
    -0.66
     retire
    -0.65
    division
    -0.64
    chnology
    -0.64
     intimidated
    -0.64
     submer
    -0.63
    POSITIVE LOGITS
    aband
    0.88
     Kant
    0.84
     Scholar
    0.84
    arta
    0.80
    ijn
    0.76
    Eye
    0.76
    76561
    0.76
     Goods
    0.74
    onom
    0.72
    ãĥķãĤ©
    0.70
    Activations Density 0.022%

    No Known Activations