© 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. 18892
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "temporary."

    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
    gans
    -0.88
    bold
    -0.83
    eus
    -0.82
    ioch
    -0.78
    ymes
    -0.78
    sonian
    -0.78
    ongs
    -0.76
    orius
    -0.75
    eers
    -0.73
    riad
    -0.73
    POSITIVE LOGITS
     restraining
    1.03
     accommodation
    0.96
     temporary
    0.94
    porary
    0.91
     lodging
    0.86
     inval
    0.85
     temporarily
    0.82
     displacement
    0.78
     halting
    0.78
     truce
    0.77
    Activations Density 0.008%

    No Known Activations