INDEX

Explanations

specific propositions or statements

oai_token-act-pair · gpt-3.5-turbo

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

izont

-0.66

 Mane

-0.65

 Jaguar

-0.64

 Champ

-0.60

MX

-0.59

aukee

-0.59

Mi

-0.58

Tax

-0.58

throp

-0.58

IAS

-0.57

POSITIVE LOGITS

 culminated

0.86

 consequently

0.78

 resulted

0.77

cher

0.74

 fateful

0.72

 secondly

0.71

 contradicts

0.70

eatures

0.69

 furthermore

0.69

 reconc

0.69

Activations Density 0.109%

specific propositions or statements

the word "that" in various contexts

No Comments

No Known Activations