INDEX

Explanations

passages mentioning the concept of something being considered or evaluated

oai_token-act-pair · gpt-3.5-turbo

instances of the word "considered" in 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inas

-0.66

Ring

-0.64

sheets

-0.62

driver

-0.60

 Alley

-0.59

 Lann

-0.58

adra

-0.58

cies

-0.57

 Longh

-0.57

 Planes

-0.57

POSITIVE LOGITS

phas

0.94

 favorably

0.91

 considered

0.77

 Tradable

0.76

 "$:/

0.74

é¾įå¥ĳå£«

0.74

ilitarian

0.70

MFT

0.69

æĺ¯

0.68

aimon

0.67

Activations Density 0.023%

passages mentioning the concept of something being considered or evaluated

instances of the word "considered" in various contexts

No Comments

No Known Activations