INDEX

Explanations

words containing "ind" followed by a high activation value of 9 or 10

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ind" in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

OPLE

-0.79

sonian

-0.74

MQ

-0.73

BuyableInstoreAndOnline

-0.72

veyard

-0.72

ffen

-0.69

zzo

-0.68

 Fenrir

-0.67

anwhile

-0.66

cca

-0.66

POSITIVE LOGITS

ented

1.08

etermin

1.04

ivid

1.04

ind

0.98

irection

0.94

ents

0.92

oled

0.90

irect

0.89

ocument

0.87

icol

0.87

Activations Density 0.008%

words containing "ind" followed by a high activation value of 9 or 10

occurrences of the substring "ind" in words

No Comments

No Known Activations