© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    comfort and safety-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    words associated with safety, security, and support

    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
     blat
    -0.69
    asus
    -0.65
    omorphic
    -0.65
    asted
    -0.65
    hemat
    -0.63
    ailand
    -0.59
     preval
    -0.59
    buff
    -0.59
    ophile
    -0.58
     disproportion
    -0.58
    POSITIVE LOGITS
     amidst
    0.87
     afforded
    0.79
     amid
    0.78
    ANCE
    0.77
     awaits
    0.76
     srfAttach
    0.73
     cushion
    0.70
    rieve
    0.70
    mate
    0.68
    mates
    0.67
    Activations Density 0.301%

    No Known Activations