© 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. 3368
    Prev
    Next
    INDEX
    Explanations

    references to events that are hoped to be avoided or prevented

    oai_token-act-pair · gpt-3.5-turbo

    expressions of regret or wishes about past events

    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
     inspecting
    -0.70
     retaining
    -0.69
     inspect
    -0.68
    lication
    -0.66
    ©¶æ¥µ
    -0.65
    Reviewer
    -0.65
     eager
    -0.64
     Parables
    -0.62
    ettings
    -0.60
     seeking
    -0.59
    POSITIVE LOGITS
     happen
    1.42
     happening
    1.41
     happened
    1.35
     happ
    1.21
     happens
    1.12
     Happ
    1.05
     transpired
    1.03
     occurred
    1.03
     occur
    1.01
     occurring
    1.01
    Activations Density 0.634%

    No Known Activations