© 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. 1395
    Prev
    Next
    INDEX
    Explanations

    the word "saddle" occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions and variations of sadness and burdensomeness

    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
    assetsadobe
    -0.65
     Goth
    -0.65
     McDonnell
    -0.64
     Webster
    -0.64
    DOM
    -0.64
    STD
    -0.64
    aphael
    -0.61
    perties
    -0.60
     Scotia
    -0.59
     comprehension
    -0.59
    POSITIVE LOGITS
     sadd
    1.05
    rums
    0.91
    bags
    0.85
     saddle
    0.83
    rack
    0.78
    stra
    0.77
    led
    0.77
    les
    0.77
    alore
    0.76
    itudes
    0.73
    Activations Density 0.008%

    No Known Activations