© 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. 7817
    Prev
    Next
    INDEX
    Explanations

    words related to approval, disapproval, and assessment

    oai_token-act-pair · gpt-3.5-turbo

    words related to approval and assessment processes

    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
     Copenhagen
    -0.75
    dot
    -0.73
    aer
    -0.68
     Canterbury
    -0.66
     Worcester
    -0.65
     Abyssal
    -0.65
     Hollow
    -0.64
    ãĥĥãĥī
    -0.64
     Equality
    -0.64
     Tale
    -0.64
    POSITIVE LOGITS
    appro
    1.30
    ved
    0.90
    vals
    0.90
    pport
    0.90
    roach
    0.85
    ving
    0.85
    spective
    0.85
    issance
    0.85
     Appro
    0.84
    rien
    0.83
    Activations Density 0.012%

    No Known Activations