© 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. 6-RES-JB
    11. 7687
    Prev
    Next
    INDEX
    Explanations

    phrases related to buying, obtaining, or gaining possession of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "acquire" and its variations, indicating a focus on acquisition concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.88
    acea
    -0.79
    example
    -0.74
    Fed
    -0.70
    heet
    -0.70
    wayne
    -0.67
    cgi
    -0.66
    atever
    -0.66
    eday
    -0.64
    PsyNetMessage
    -0.64
    POSITIVE LOGITS
    ments
    0.95
    ment
    0.85
    Interstitial
    0.78
    ader
    0.77
    isitions
    0.70
     trophies
    0.68
     intangible
    0.68
    mentation
    0.68
     ownership
    0.67
     holdings
    0.66
    Activations Density 0.026%

    No Known Activations