Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20698
    Prev
    Next
    INDEX
    Explanations

    phrases related to product reviews

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quality or high standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.93
    leground
    -0.84
    SHARE
    -0.82
    uclear
    -0.78
    urden
    -0.78
    ÑĮ
    -0.77
    ����
    -0.76
    اØ
    -0.76
    ailable
    -0.74
    20439
    -0.74
    POSITIVE LOGITS
     downside
    1.26
     biggest
    1.14
     drawback
    1.08
     fact
    1.04
     sheer
    1.04
    oret
    1.02
     coolest
    1.01
     simplicity
    1.01
     slightest
    1.01
     texture
    0.99
    Activations Density 0.218%

    No Known Activations