INDEX

Explanations

phrases related to athletic performance and achievements

oai_token-act-pair · gpt-3.5-turbo

references to athletic performance and physical measurements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

gross

-0.82

offer

-0.74

iots

-0.73

orno

-0.70

addafi

-0.68

Invalid

-0.68

Cause

-0.67

 Oops

-0.67

icious

-0.67

Population

-0.66

POSITIVE LOGITS

 workouts

0.97

 outings

0.95

 scrim

0.93

 adversity

0.92

 drills

0.92

 defenders

0.88

 teammates

0.88

 rookies

0.87

 Rookie

0.86

 transitions

0.83

Activations Density 0.293%

phrases related to athletic performance and achievements

references to athletic performance and physical measurements

No Known Activations