© 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. 4020
    Prev
    Next
    INDEX
    Explanations

    phrases related to punishment or punitive actions

    oai_token-act-pair · gpt-3.5-turbo

    references to punishment in various contexts

    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
    eds
    -0.83
    Champ
    -0.77
    street
    -0.69
    ocaly
    -0.69
    clus
    -0.68
    opic
    -0.68
    timer
    -0.67
    ortment
    -0.65
    sky
    -0.64
    park
    -0.64
    POSITIVE LOGITS
     punish
    1.22
     punished
    1.16
     punishing
    0.99
     harshly
    0.96
     punishment
    0.91
     punishments
    0.85
     disadvant
    0.82
     rewarded
    0.82
     penal
    0.80
     unfairly
    0.78
    Activations Density 0.012%

    No Known Activations