© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14518
    Prev
    Next
    INDEX
    Explanations

    phrases related to being impacted or influenced

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups that are impacted by various situations or events

    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
    ALK
    -0.75
    IDE
    -0.72
    atom
    -0.71
     Haku
    -0.70
    OVA
    -0.68
    TERN
    -0.68
    çĦ
    -0.67
    puted
    -0.67
    ATT
    -0.67
    Blade
    -0.67
    POSITIVE LOGITS
     affected
    1.24
     impacted
    1.17
     adversely
    1.12
     effected
    1.06
     unaffected
    0.94
     impact
    0.88
     negatively
    0.87
     affect
    0.87
     impacts
    0.87
    affected
    0.82
    Activations Density 0.013%

    No Known Activations