© 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. 8995
    Prev
    Next
    INDEX
    Explanations

    expressions related to gratitude or value recognition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of appreciation

    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
     compuls
    -0.79
    infect
    -0.73
    zh
    -0.72
    destruct
    -0.70
    nuclear
    -0.69
    host
    -0.66
    packed
    -0.65
     carcin
    -0.64
    orig
    -0.62
     tumor
    -0.62
    POSITIVE LOGITS
     appreciation
    1.46
    reciation
    0.97
    ð
    0.89
    ocity
    0.87
     appreciate
    0.86
     mathemat
    0.86
    gdala
    0.85
     uncond
    0.83
     Pwr
    0.82
    awaru
    0.81
    Activations Density 0.008%

    No Known Activations