© 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. 1-RES-JB
    11. 17977
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to paradoxes

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to paradoxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.83
    gars
    -0.75
    Ķ
    -0.68
    ACTED
    -0.67
    RAW
    -0.67
    rations
    -0.66
    asts
    -0.65
    OTT
    -0.65
    astered
    -0.64
    gur
    -0.63
    POSITIVE LOGITS
     paradox
    1.41
     Paradox
    1.11
    ical
    0.97
    ioned
    0.96
    ically
    0.88
     Despair
    0.82
    ively
    0.77
    istically
    0.74
    es
    0.74
    ional
    0.73
    Activations Density 0.004%

    No Known Activations