© 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. 0-RES-JB
    11. 16562
    Prev
    Next
    INDEX
    Explanations

    words related to historical or metaphorical contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to allegorical and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inhibitor
    -0.75
     amp
    -0.64
     AV
    -0.63
     inhibitors
    -0.62
     autop
    -0.62
     channels
    -0.61
     accord
    -0.60
     leak
    -0.60
     CC
    -0.59
     startup
    -0.59
    POSITIVE LOGITS
    orical
    4.26
    orically
    3.61
    oric
    2.20
    orians
    1.73
    ory
    1.70
    ories
    1.61
    orian
    1.59
    ysical
    1.50
    orie
    1.43
    orial
    1.38
    Activations Density 0.017%

    No Known Activations