© 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. 7-RES-JB
    11. 20013
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of creators, artists, or contributors associated with various works and submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of creators or contributors in different fields

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resil
    -0.80
     wagon
    -0.77
     lockdown
    -0.73
     safely
    -0.71
    jriwal
    -0.69
     job
    -0.69
     positives
    -0.67
     belie
    -0.67
     guarded
    -0.67
     offence
    -0.66
    POSITIVE LOGITS
    rak
    0.80
    frey
    0.74
    ixel
    0.74
     Thom
    0.73
    abel
    0.72
     Magazine
    0.71
     Interactive
    0.70
     (@
    0.70
    minster
    0.70
    ij
    0.69
    Activations Density 0.290%

    No Known Activations