INDEX

Explanations

phrases related to comparisons or contrasts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating comparisons or contrasts

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

opsis

-0.63

 Procedure

-0.58

Writer

-0.57

forcement

-0.55

CRE

-0.55

uthor

-0.53

ploy

-0.51

orney

-0.51

SELECT

-0.50

TION

-0.50

POSITIVE LOGITS

 differently

0.64

âĺ

0.59

animate

0.59

vec

0.59

hovah

0.54

 yearly

0.54

different

0.51

 airplanes

0.49

erent

0.49

 interchange

0.48

Activations Density 1.047%

phrases related to comparisons or contrasts

phrases indicating comparisons or contrasts

No Comments

No Known Activations