© 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. 9-RES-JB
    11. 16369
    Prev
    Next
    INDEX
    Explanations

    activities related to socializing and spending time with others

    oai_token-act-pair · gpt-3.5-turbo

    activities and social interactions among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confirmation
    -0.72
    rimination
    -0.68
     guarantee
    -0.66
     precedent
    -0.65
     liability
    -0.65
     unequivocally
    -0.64
    enta
    -0.64
    etheus
    -0.62
    formation
    -0.61
     unequiv
    -0.61
    POSITIVE LOGITS
    ercise
    0.87
     merry
    0.80
     furiously
    0.79
     leisure
    0.78
     snacks
    0.78
     scaven
    0.77
     hobbies
    0.77
     beers
    0.76
     toys
    0.76
     cocktails
    0.75
    Activations Density 0.483%

    No Known Activations