© 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. 6-RES-JB
    11. 20390
    Prev
    Next
    INDEX
    Explanations

    phrases related to thorough investigation or examination

    oai_token-act-pair · gpt-3.5-turbo

    the word "thoroughly" and its variations in the context of detailed or careful actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.75
    artifacts
    -0.73
    ERY
    -0.73
    eways
    -0.73
    eries
    -0.66
    quickShipAvailable
    -0.66
    mere
    -0.65
    llor
    -0.65
     tendency
    -0.65
     tendencies
    -0.65
    POSITIVE LOGITS
     researched
    0.97
     entertained
    0.90
     tested
    0.86
    ãĤ©
    0.85
    ãĤ£
    0.82
     vetted
    0.80
     exhausted
    0.79
     examined
    0.78
     impressed
    0.76
     briefed
    0.76
    Activations Density 0.031%

    No Known Activations