© 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. 6488
    Prev
    Next
    INDEX
    Explanations

    items that a person is likely to purchase or consider purchasing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consumer behavior and purchasing decisions

    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
    arak
    -0.67
     Cipher
    -0.66
     Dawson
    -0.63
     Railway
    -0.63
     Dictionary
    -0.63
     Inspector
    -0.62
    ģĸ
    -0.62
     âĵĺ
    -0.60
     Architects
    -0.60
     Nanto
    -0.58
    POSITIVE LOGITS
     wrong
    0.87
     uncond
    0.84
     yourself
    0.80
     cheaply
    0.78
     Specific
    0.77
    wrong
    0.76
     yourselves
    0.74
     exclusively
    0.74
     oneself
    0.71
     solely
    0.71
    Activations Density 0.707%

    No Known Activations