© 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. 1481
    Prev
    Next
    INDEX
    Explanations

    references to operas

    oai_token-act-pair · gpt-3.5-turbo

    references to opera

    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
    animous
    -0.80
    erred
    -0.73
    adow
    -0.72
    idential
    -0.67
    later
    -0.66
    ĪĴ
    -0.65
    airy
    -0.65
    erry
    -0.64
    alien
    -0.64
    unch
    -0.63
    POSITIVE LOGITS
     opera
    1.13
     singers
    0.89
     singer
    0.85
    otomy
    0.83
    glers
    0.83
     Opera
    0.79
     traged
    0.77
     oper
    0.76
     rehearsal
    0.76
     theatre
    0.73
    Activations Density 0.005%

    No Known Activations