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

    Neuronpedia

    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. 7-RES-JB
    11. 18055
    Prev
    Next
    INDEX
    Explanations

    phrases indicating variation or dependency on certain conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word 'depending' and variations of it, indicating conditional statements or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.76
    jah
    -0.73
    together
    -0.70
    lyn
    -0.70
    Cola
    -0.68
    REAM
    -0.68
    far
    -0.68
    Wolf
    -0.67
    RL
    -0.66
    uld
    -0.64
    POSITIVE LOGITS
     circumstances
    0.92
     whether
    0.82
     behalf
    0.80
     circumstance
    0.77
     how
    0.76
     jurisd
    0.74
     factors
    0.73
     occasion
    0.72
     prevailing
    0.71
     severity
    0.71
    Activations Density 0.038%

    No Known Activations