INDEX

Explanations

words related to a specific object: "tank"

oai_token-act-pair · gpt-3.5-turbo

references to tanks

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

âĸ¬

-0.94

theless

-0.72

BOOK

-0.70

————

-0.67

 DMCA

-0.67

 Brotherhood

-0.67

teness

-0.64

éĹ

-0.64

å¥³

-0.63

Lod

-0.63

POSITIVE LOGITS

erness

1.14

ards

1.03

mates

0.98

yard

0.96

ard

0.96

tank

0.93

agers

0.93

pit

0.88

ered

0.87

buster

0.87

Activations Density 0.034%

words related to a specific object: "tank"

references to tanks

No Comments

No Known Activations