© 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. 8-RES-JB
    11. 4062
    Prev
    Next
    INDEX
    Explanations

    the word 'of' occurring in various contexts and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rates or increases of various phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roots
    -0.93
    æĦ
    -0.87
     Aires
    -0.85
    minus
    -0.85
    nis
    -0.84
    selves
    -0.84
    redients
    -0.76
    äºĶ
    -0.75
    bags
    -0.74
    deck
    -0.74
    POSITIVE LOGITS
     occurrence
    1.17
     decline
    1.01
     progress
    0.96
     decay
    0.95
     attrition
    0.95
     escalation
    0.93
     erosion
    0.93
     deterioration
    0.92
     incidence
    0.89
     progression
    0.89
    Activations Density 0.064%

    No Known Activations