INDEX

Explanations

the word 'those'

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "those"

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

ob

-0.72

 Ness

-0.69

iness

-0.66

onis

-0.66

ARP

-0.65

SPONSORED

-0.65

shapeshifter

-0.64

ister

-0.64

Â¨

-0.62

achus

-0.62

POSITIVE LOGITS

 kinds

0.93

 pesky

0.88

 sorts

0.87

 fateful

0.73

ratulations

0.72

 guys

0.72

 sights

0.70

 interested

0.69

urg

0.69

types

0.69

Activations Density 0.065%

the word 'those'

the repeated use of the word "those"

No Comments

No Known Activations