INDEX

Explanations

phrases that indicate repeated actions or behavior

oai_token-act-pair · gpt-3.5-turbo

instances of the word "repeatedly"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reviewer

-0.92

toc

-0.79

OTA

-0.75

ghai

-0.73

soc

-0.73

ocene

-0.71

istan

-0.70

ocard

-0.68

mop

-0.66

potion

-0.66

POSITIVE LOGITS

theless

0.87

 repeated

0.84

 reaff

0.82

 interrupted

0.81

 reiter

0.80

 incarn

0.79

 unsuccessful

0.78

 reiterated

0.78

 contradict

0.77

 contradicted

0.77

Activations Density 0.025%

phrases that indicate repeated actions or behavior

instances of the word "repeatedly"

No Comments

No Known Activations