© 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. 0-RES-JB
    11. 20414
    Prev
    Next
    INDEX
    Explanations

    phrases related to detention, especially in a negative context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "detention" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buck
    -0.67
    pers
    -0.66
     Phil
    -0.64
    izers
    -0.64
    ides
    -0.64
    VP
    -0.62
    ellow
    -0.62
    thro
    -0.61
     Creator
    -0.60
     MVP
    -0.60
    POSITIVE LOGITS
     detention
    3.71
     Detention
    2.80
     detain
    2.20
     detainee
    2.06
     detainees
    1.97
     incarceration
    1.89
     detained
    1.84
     confinement
    1.81
     imprisonment
    1.78
     interrogation
    1.65
    Activations Density 0.013%

    No Known Activations