© 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. 2741
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a decision or choice

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal responsibility

    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
    hello
    -0.78
    isky
    -0.74
    iked
    -0.70
    mol
    -0.67
    anguages
    -0.67
    ense
    -0.67
    TEXT
    -0.67
    listed
    -0.66
    artifacts
    -0.66
    ãĥŁ
    -0.66
    POSITIVE LOGITS
     discretion
    1.07
     whoever
    0.91
     imagination
    0.83
     interpretation
    0.83
     judges
    0.81
     policymakers
    0.81
     professionals
    0.80
     Allaah
    0.77
     consumers
    0.74
     shoulders
    0.73
    Activations Density 0.180%

    No Known Activations