© 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. 15156
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'Maury'

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the term "ury" and its variations, likely related to specific names or phrases

    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
    eworld
    -0.82
    eared
    -0.81
    cedented
    -0.76
    hatt
    -0.74
    insula
    -0.74
    mercial
    -0.72
    olkien
    -0.72
    chart
    -0.72
    gotten
    -0.70
    etts
    -0.69
    POSITIVE LOGITS
    ury
    0.78
    stein
    0.77
    pants
    0.66
    âķIJ
    0.66
    Å«
    0.65
    outube
    0.64
    uay
    0.64
    ":""},{"
    0.63
    von
    0.63
     Sul
    0.63
    Activations Density 0.007%

    No Known Activations