© 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. 1-RES-JB
    11. 14306
    Prev
    Next
    INDEX
    Explanations

    terms related to social media

    oai_token-act-pair · gpt-3.5-turbo

    references to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wrath
    -0.70
    vasive
    -0.69
     Shinra
    -0.68
     Carm
    -0.68
    ECD
    -0.68
     Ambrose
    -0.66
     Shall
    -0.65
    gran
    -0.65
     Venom
    -0.63
     Mel
    -0.63
    POSITIVE LOGITS
    media
    1.03
     outlets
    0.98
     media
    0.91
    Media
    0.90
     outlet
    0.86
    fax
    0.82
    ifact
    0.77
    Buzz
    0.76
     mogul
    0.74
     platforms
    0.73
    Activations Density 0.020%

    No Known Activations