© 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. 2-RES-JB
    11. 947
    Prev
    Next
    INDEX
    Explanations

    words ending with "owers"

    oai_token-act-pair · gpt-4-turbo

    phrases related to power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to power dynamics and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERAL
    -0.72
    âĸ¬
    -0.69
    Philipp
    -0.69
    ר
    -0.65
    ׾
    -0.64
    ric
    -0.64
    cs
    -0.64
    Condition
    -0.64
    Pacific
    -0.63
    à©
    -0.63
    POSITIVE LOGITS
    chwitz
    0.96
    hops
    0.96
    peed
    0.93
    ynthesis
    0.92
    kinson
    0.91
    pace
    0.89
    ktop
    0.88
    hift
    0.88
    uits
    0.87
    creen
    0.83
    Activations Density 0.008%

    No Known Activations