© 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. 8-RES-JB
    11. 163
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions performed by or towards someone or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agency or attribution, specifically the use of "by" to denote who performed an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BSD
    -0.83
    heimer
    -0.80
    clips
    -0.78
    redits
    -0.76
    âľ
    -0.75
    bia
    -0.74
    etta
    -0.72
    uality
    -0.72
    ational
    -0.70
    prototype
    -0.70
    POSITIVE LOGITS
     virtue
    1.16
     superiors
    0.92
     strangers
    0.76
     supervisors
    0.76
     passers
    0.74
     landlords
    0.73
     STATS
    0.72
     Hilton
    0.72
     employers
    0.72
    chance
    0.71
    Activations Density 0.145%

    No Known Activations