© 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. 13509
    Prev
    Next
    INDEX
    Explanations

    references to diversity or multi-racial individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "multicultural" or "multiracial" themes

    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
    HOME
    -0.88
    _>
    -0.78
    OCK
    -0.77
    YL
    -0.76
    INESS
    -0.75
    çĶ°
    -0.74
    OPLE
    -0.74
    WT
    -0.74
    姫
    -0.73
     Wolves
    -0.73
    POSITIVE LOGITS
    icol
    1.24
    ivariate
    1.15
    ilingual
    1.11
    ilateral
    1.08
    iversal
    1.05
    ilater
    1.04
    ivari
    1.04
    amorph
    0.99
     challeng
    0.96
    iques
    0.96
    Activations Density 0.004%

    No Known Activations