© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    adjective or verb forms indicating perception or judgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seem" and its variations, indicating perceptions or beliefs about individuals or situations

    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
    estern
    -0.76
    ilts
    -0.71
    ests
    -0.70
    ainers
    -0.68
    ribution
    -0.67
    zb
    -0.66
     Fahrenheit
    -0.63
    OOL
    -0.61
     VIDEOS
    -0.60
    ffen
    -0.60
    POSITIVE LOGITS
     poised
    0.96
     awfully
    0.89
     eager
    0.88
     oddly
    0.88
     intent
    0.88
     strangely
    0.87
     reluctant
    0.87
     confused
    0.86
     hesitant
    0.83
     innocuous
    0.83
    Activations Density 0.056%

    No Known Activations