INDEX

Explanations

phrases related to rates or frequency of occurrence

oai_token-act-pair · gpt-3.5-turbo

variations of the word "rate" associated with numerical measurements or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Aires

-0.88

enegger

-0.80

arij

-0.78

iami

-0.78

quickShipAvailable

-0.77

paio

-0.76

bley

-0.76

 Jakarta

-0.76

IRT

-0.74

emis

-0.73

POSITIVE LOGITS

payers

1.43

payer

1.18

Beer

0.84

(%)

0.84

Rate

0.80

 averages

0.75

ologies

0.74

Upload

0.74

hyde

0.74

 rates

0.74

Activations Density 0.031%

phrases related to rates or frequency of occurrence

variations of the word "rate" associated with numerical measurements or occurrences

No Comments

No Known Activations