© 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. 8-RES-JB
    11. 14837
    Prev
    Next
    INDEX
    Explanations

    rumors and gossip

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rum" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.76
     Levi
    -0.63
     learning
    -0.62
     humans
    -0.61
     Alexandria
    -0.60
     Egyptians
    -0.60
    Madison
    -0.58
     Dangerous
    -0.57
     Emb
    -0.57
     Harmony
    -0.57
    POSITIVE LOGITS
    pled
    1.30
    oured
    1.16
    inating
    1.16
    atis
    1.15
    ble
    1.11
    inatory
    1.09
    aceutical
    0.98
    pty
    0.96
    ination
    0.94
    ored
    0.94
    Activations Density 0.021%

    No Known Activations