© 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. 3-RES-JB
    11. 15111
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orno
    -0.78
    yi
    -0.76
    iry
    -0.74
    agents
    -0.69
     betrayal
    -0.68
    amy
    -0.67
     crime
    -0.66
    oras
    -0.65
    plates
    -0.65
    lins
    -0.64
    POSITIVE LOGITS
     exting
    0.97
     safely
    0.96
     conclud
    0.95
     outweigh
    0.81
     evacuated
    0.80
    ufact
    0.79
    veland
    0.76
    ãĤ©
    0.75
     transitioned
    0.75
     detonated
    0.75
    Activations Density 0.012%

    No Known Activations