© 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. 8-RES-JB
    11. 18699
    Prev
    Next
    INDEX
    Explanations

    warnings or negative consequences related to various actions or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing negative socio-economic impacts and challenges

    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
     compliment
    -0.64
    estones
    -0.64
    poke
    -0.63
    iple
    -0.63
     complimentary
    -0.63
    nesday
    -0.63
     nods
    -0.62
    Happy
    -0.61
    nice
    -0.61
     greeting
    -0.61
    POSITIVE LOGITS
     destabil
    1.21
     havoc
    1.15
     worsening
    1.10
     exacerb
    1.09
     jeopard
    1.08
     exacerbate
    1.08
     crippling
    1.07
     worsen
    1.07
     worsened
    1.05
     instability
    1.04
    Activations Density 1.321%

    No Known Activations