© 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. 1500
    Prev
    Next
    INDEX
    Explanations

    comparisons between different groups, with a specific focus on specific groups being compared to their counterparts

    oai_token-act-pair · gpt-3.5-turbo

    references to counterparts in various contexts, emphasizing comparisons or relationships between groups or entities

    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
    aping
    -0.76
    cer
    -0.73
    cloth
    -0.73
    raz
    -0.71
    wood
    -0.68
    estern
    -0.68
    frey
    -0.68
     Fulton
    -0.65
    ousel
    -0.65
    Chain
    -0.62
    POSITIVE LOGITS
     counterparts
    1.16
     counterpart
    1.02
    hip
    0.89
    DragonMagazine
    0.88
     reluct
    0.79
    itutes
    0.78
    itute
    0.78
    isons
    0.76
     thereof
    0.74
    MpServer
    0.74
    Activations Density 0.007%

    No Known Activations