© 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. 7-RES-JB
    11. 23427
    Prev
    Next
    INDEX
    Explanations

    phrases related to spending money or paying a specified amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial expenditure or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aghd
    -0.61
    iw
    -0.59
    reflect
    -0.59
    Machine
    -0.59
    cius
    -0.59
    AAF
    -0.58
    ileaks
    -0.58
     Underground
    -0.58
     linkage
    -0.57
    amazon
    -0.56
    POSITIVE LOGITS
     concessions
    0.78
    hire
    0.74
     victories
    0.73
     pts
    0.71
     Vaughn
    0.70
     scraps
    0.68
     spit
    0.67
     praise
    0.66
     swat
    0.65
     havoc
    0.65
    Activations Density 0.121%

    No Known Activations