© 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. 9913
    Prev
    Next
    INDEX
    Explanations

    phrases related to the history of particular actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a history of negative or unethical behavior

    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
    Zone
    -0.78
    raints
    -0.71
     Tycoon
    -0.70
    pload
    -0.70
    bern
    -0.70
    Wave
    -0.70
    atar
    -0.70
    emouth
    -0.69
    hap
    -0.69
    nette
    -0.69
    POSITIVE LOGITS
     abuse
    0.94
     hostility
    0.86
     abusing
    0.85
     excellence
    0.84
     tink
    0.84
     colonialism
    0.84
     persecution
    0.83
     success
    0.83
     sorts
    0.82
     experimentation
    0.82
    Activations Density 0.103%

    No Known Activations