© 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. 2-RES-JB
    11. 19875
    Prev
    Next
    INDEX
    Explanations

    mentions of social media interactions, specifically retweets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media interactions and environmental reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oom
    -0.86
    Cube
    -0.78
    pert
    -0.75
    properties
    -0.73
    Ultra
    -0.73
    bestos
    -0.70
    Dub
    -0.67
    isine
    -0.64
    oooo
    -0.63
    ite
    -0.62
    POSITIVE LOGITS
    ribut
    0.84
    imates
    0.74
     guiActiveUn
    0.73
    ezvous
    0.72
    ère
    0.69
    psey
    0.67
    uple
    0.66
     Nunes
    0.66
     generals
    0.65
    umbn
    0.65
    Activations Density 0.029%

    No Known Activations