INDEX

Explanations

phrases with the word "added" indicating additional information or commentary

oai_token-act-pair · gpt-3.5-turbo

instances of the word "added" and its context in relation to statements or declarations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ardless

-0.75

Bos

-0.66

cies

-0.65

 Bram

-0.64

bin

-0.63

view

-0.62

FL

-0.62

 Twin

-0.62

MAT

-0.62

bred

-0.62

POSITIVE LOGITS

endum

0.92

itivity

0.85

ictions

0.84

itionally

0.84

eele

0.80

redd

0.78

anguage

0.78

isson

0.77

 urgency

0.77

mission

0.77

Activations Density 0.038%

phrases with the word "added" indicating additional information or commentary

instances of the word "added" and its context in relation to statements or declarations

No Comments

No Known Activations