© 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. 11-RES-JB
    11. 24547
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express significant or extreme evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Respond
    -0.73
    units
    -0.71
    groups
    -0.69
    achine
    -0.69
    roups
    -0.66
    ULTS
    -0.65
    orig
    -0.64
     rates
    -0.63
    alks
    -0.62
    TextColor
    -0.62
    POSITIVE LOGITS
     understatement
    1.16
     boon
    1.15
     nightmare
    1.13
     blessing
    1.07
     miracle
    1.04
     shame
    1.03
     disaster
    1.01
     coup
    1.00
     disappointment
    1.00
     feat
    0.99
    Activations Density 0.163%

    No Known Activations