© 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. 3-RES-JB
    11. 8787
    Prev
    Next
    INDEX
    Explanations

    terms related to modern times or modern concepts

    oai_token-act-pair · gpt-3.5-turbo

    the concept of modernity

    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
    Bone
    -0.87
    kick
    -0.74
    OTH
    -0.72
    vana
    -0.72
    Recommend
    -0.72
    channelAvailability
    -0.70
    Downloadha
    -0.70
    Keys
    -0.70
    Jar
    -0.70
    ---------
    -0.68
    POSITIVE LOGITS
    isation
    1.10
    ization
    0.90
    isers
    0.90
     incarnation
    0.88
     era
    0.88
    izing
    0.87
     sensibilities
    0.86
    izations
    0.86
    itized
    0.84
    modern
    0.84
    Activations Density 0.022%

    No Known Activations