© 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. 1-RES-JB
    11. 7625
    Prev
    Next
    INDEX
    Explanations

    references to the acquisition or purchase of something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "acquire"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dwarves
    -0.70
     Weeks
    -0.70
     Glover
    -0.68
     Drift
    -0.68
     Nadu
    -0.67
     Luxem
    -0.66
    OPLE
    -0.65
     Frieza
    -0.63
    DAY
    -0.63
     Bolton
    -0.63
    POSITIVE LOGITS
    isitions
    1.41
    ittal
    1.34
    acqu
    1.33
    isition
    1.23
     Acqu
    1.02
    ired
    0.94
    ille
    0.94
    ision
    0.94
    iences
    0.94
    inis
    0.93
    Activations Density 0.011%

    No Known Activations