© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    terms related to the software Adobe

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "obe," indicating a strong focus on brands or specific entities related to "obe."

    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
    iments
    -0.66
    idy
    -0.66
    imental
    -0.64
    death
    -0.62
     Winchester
    -0.60
    displayText
    -0.59
     impossibility
    -0.59
    sing
    -0.59
    entially
    -0.59
    allic
    -0.58
    POSITIVE LOGITS
    obe
    1.11
    leck
    0.96
    pedia
    0.92
    zeb
    0.89
     Bryant
    0.79
    zes
    0.77
    opsis
    0.75
    cean
    0.73
    etooth
    0.72
    bies
    0.72
    Activations Density 0.006%

    No Known Activations