© 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. 2-RES-JB
    11. 4525
    Prev
    Next
    INDEX
    Explanations

    mentions of purchasing something using some form of payment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to purchasing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.67
    inas
    -0.66
    doi
    -0.63
    pmwiki
    -0.63
    inav
    -0.62
    odor
    -0.62
    osa
    -0.61
    ousy
    -0.60
    uum
    -0.60
     pH
    -0.58
    POSITIVE LOGITS
    iture
    1.08
     buying
    0.92
     buy
    0.89
     buys
    0.88
     purchases
    0.87
     bought
    0.84
     purchasing
    0.83
    itures
    0.80
    tery
    0.75
    ħĭ
    0.74
    Activations Density 0.030%

    No Known Activations