INDEX

Explanations

phrases related to superlatives or extremes, especially those related to rankings within a category

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize something being significant or prominent in the world

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

merce

-0.96

imon

-0.92

paio

-0.82

urations

-0.81

aturday

-0.81

sbm

-0.79

conserv

-0.79

odox

-0.74

uper

-0.74

Corp

-0.73

POSITIVE LOGITS

 premiere

0.79

 Confederation

0.73

 championships

0.71

 economy

0.71

 championship

0.71

 arena

0.70

wide

0.70

oland

0.68

 renowned

0.68

building

0.65

Activations Density 0.045%

phrases related to superlatives or extremes, especially those related to rankings within a category

phrases that emphasize something being significant or prominent in the world

No Comments

No Known Activations