INDEX

Explanations

phrases related to citing sources or attributing information

oai_token-act-pair · gpt-3.5-turbo

the phrase "according to" indicating sourced information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

iste

-0.78

NetMessage

-0.76

ocr

-0.70

ennial

-0.70

viation

-0.69

itaire

-0.66

-,

-0.66

ophobia

-0.66

ãĥİ

-0.66

soDeliveryDate

-0.66

POSITIVE LOGITS

 sources

1.06

 reports

0.98

 excerpts

0.98

reports

0.96

 Reuters

0.91

 documents

0.88

 testimony

0.87

 STATS

0.86

 Bloomberg

0.85

 Politico

0.84

Activations Density 0.074%

phrases related to citing sources or attributing information

the phrase "according to" indicating sourced information

No Comments

No Known Activations