INDEX

Explanations

terms related to perspectives and standpoints

oai_token-act-pair · gpt-3.5-turbo

references to different viewpoints or perspectives on a topic

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

weet

-0.64

çļ

-0.63

rhy

-0.62

selling

-0.61

tro

-0.59

usive

-0.59

ifying

-0.58

und

-0.58

 grun

-0.58

POSITIVE LOGITS

 perspective

1.23

 standpoint

1.20

 viewpoint

1.00

 perspectives

0.99

 Perspective

0.87

 vantage

0.83

POV

0.77

points

0.74

finder

0.74

 viewpoints

0.73

Activations Density 0.019%

terms related to perspectives and standpoints

references to different viewpoints or perspectives on a topic

No Comments

No Known Activations