© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9008
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thing" being used

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize certainty or definitive statements

    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
    inav
    -0.87
    cled
    -0.72
    ONSORED
    -0.66
    irl
    -0.65
     anonymity
    -0.64
     Tos
    -0.64
    osponsors
    -0.63
    gaard
    -0.62
    cean
    -0.60
    ãĥ¥
    -0.60
    POSITIVE LOGITS
     happens
    0.92
     happened
    0.89
    iverse
    0.88
     Valiant
    0.79
     happ
    0.77
     happening
    0.74
     transpired
    0.72
    ername
    0.69
    ially
    0.67
    Else
    0.66
    Activations Density 0.036%

    No Known Activations