INDEX

Explanations

phrases related to specific names or titles, particularly those containing the word "Bron"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Bron" or variations of it

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

URA

-0.72

CV

-0.72

 caution

-0.68

 bearer

-0.64

aeda

-0.63

uras

-0.63

 relativity

-0.62

 horm

-0.62

 Madness

-0.61

Attach

-0.60

POSITIVE LOGITS

zes

1.04

zos

1.02

ze

0.97

wen

0.92

arest

0.91

fman

0.88

erd

0.88

xia

0.88

 Bron

0.87

utical

0.85

Activations Density 0.059%

phrases related to specific names or titles, particularly those containing the word "Bron"

mentions of the term "Bron" or variations of it

No Comments

No Known Activations