INDEX

Explanations

terms related to athletics or sports

oai_token-act-pair · gpt-3.5-turbo

terms related to athletics and athletic programs

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

oys

-0.76

ppelin

-0.71

later

-0.70

enthal

-0.68

ãĥĥãĥī

-0.68

orah

-0.67

ered

-0.66

lessly

-0.65

Ðº

-0.64

sky

-0.64

POSITIVE LOGITS

 athletic

0.87

 Athletic

0.84

 apparel

0.82

 footwear

0.77

 minded

0.75

limits

0.75

 trainer

0.75

 trainers

0.74

 commissions

0.73

wear

0.71

Activations Density 0.014%

terms related to athletics or sports

terms related to athletics and athletic programs

No Known Activations