© 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. 901
    Prev
    Next
    INDEX
    Explanations

    mentions of job changes or promotions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to job changes or career advancements

    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
     magazines
    -0.41
     analogy
    -0.40
     bribe
    -0.40
     metaphors
    -0.39
     noun
    -0.39
     idiots
    -0.39
     collide
    -0.38
     Coke
    -0.38
     wills
    -0.38
     sauces
    -0.38
    POSITIVE LOGITS
    Ě
    0.86
    ė
    0.86
    ē
    0.86
    ú
    0.86
    ü
    0.86
    Č
    0.86
    ù
    0.86
    Ĉ
    0.86
    ğ
    0.86
    ā
    0.86
    Activations Density 2.288%

    No Known Activations