INDEX

Explanations

phrases indicating similarities or comparisons

oai_token-act-pair · gpt-3.5-turbo

comparisons emphasizing similarity across various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 caches

-0.66

TAG

-0.66

pal

-0.66

 helicop

-0.63

LIM

-0.63

 overrun

-0.62

 outwe

-0.60

 extras

-0.60

maj

-0.59

 premie

-0.59

POSITIVE LOGITS

²¾

0.84

same

0.81

 Tradable

0.79

hov

0.79

ablishment

0.78

 Berm

0.78

ovie

0.77

^^^^

0.77

Ö¼

0.76

":"/

0.74

Activations Density 0.290%

phrases indicating similarities or comparisons

comparisons emphasizing similarity across various contexts

No Known Activations