© 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. 4-RES-JB
    11. 20829
    Prev
    Next
    INDEX
    Explanations

    instances of words related to taking ownership or responsibility, particularly in a negative context

    oai_token-act-pair · gpt-3.5-turbo

    variations of words related to plagiarism and memory-related concepts

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

    No Comments

    Negative Logits
     eminent
    -0.65
    osponsors
    -0.55
     Decay
    -0.54
     grounding
    -0.53
     recl
    -0.53
     refriger
    -0.52
     unrestricted
    -0.52
    asive
    -0.52
     Cont
    -0.52
    bies
    -0.51
    POSITIVE LOGITS
    Sov
    0.89
    oute
    0.68
    aneous
    0.67
    çīĪ
    0.67
    chnology
    0.67
    aneously
    0.66
     rall
    0.65
    lete
    0.65
    roman
    0.61
     PowerPoint
    0.61
    Activations Density 0.126%

    No Known Activations