INDEX

Explanations

dates and periods of time, specifically referencing events that happened a certain number of years ago

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "ago," particularly in various contexts indicating time

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 uniqueness

-0.86

 simultaneous

-0.76

 determination

-0.72

 similarity

-0.70

 similarities

-0.69

 mobility

-0.68

 suspic

-0.68

 emphasis

-0.66

 intensity

-0.66

 comfort

-0.66

POSITIVE LOGITS

ago

1.34

vernment

1.29

allo

0.97

edia

0.96

opa

0.94

zzi

0.88

onte

0.87

etta

0.85

onz

0.84

wright

0.81

Activations Density 0.003%

dates and periods of time, specifically referencing events that happened a certain number of years ago

the occurrence of the word "ago," particularly in various contexts indicating time

No Known Activations