INDEX

Explanations

phrases related to directions (left or right) or layout (eg. "left hand side")

oai_token-act-pair · gpt-3.5-turbo

expressions related to creation and directionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

anut

-0.72

trap

-0.71

 Flavoring

-0.70

exempt

-0.70

prep

-0.69

GW

-0.69

iasco

-0.66

estic

-0.66

imum

-0.65

ERN

-0.64

POSITIVE LOGITS

 flank

0.82

 axis

0.77

hander

0.75

 latitude

0.70

 navigation

0.70

 arrow

0.70

 Arrow

0.67

 aperture

0.66

 arrows

0.66

 citizenship

0.65

Activations Density 0.170%

phrases related to directions (left or right) or layout (eg. "left hand side")

expressions related to creation and directionality

No Comments

No Known Activations