© 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. 15090
    Prev
    Next
    INDEX
    Explanations

    specific names or terms of individuals or organizations containing "Lie" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Lie" in various contexts

    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
    arthy
    -0.77
    icable
    -0.74
    akra
    -0.72
    ahime
    -0.72
    orsi
    -0.68
    illed
    -0.66
    oulos
    -0.66
    icans
    -0.65
    smart
    -0.65
    anted
    -0.65
    POSITIVE LOGITS
    utenant
    1.34
     Lie
    1.24
    Lie
    1.06
    uten
    0.99
    lie
    0.91
    ge
    0.85
    gey
    0.83
    itle
    0.81
    pard
    0.81
     detector
    0.80
    Activations Density 0.010%

    No Known Activations