INDEX

Explanations

mentions of the acronym "IG" with various numerical values, potentially related to a specific entity or concept

oai_token-act-pair · gpt-3.5-turbo

references to specific companies and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

etheless

-0.73

Mub

-0.72

theless

-0.70

 Franch

-0.68

wikipedia

-0.67

birth

-0.66

selves

-0.65

 Shore

-0.65

 Dresden

-0.64

ength

-0.64

POSITIVE LOGITS

GER

1.16

regor

1.12

IG

1.08

INAL

1.03

vernment

0.97

allery

0.95

gers

0.94

NING

0.94

HER

0.94

RD

0.93

Activations Density 0.005%

mentions of the acronym "IG" with various numerical values, potentially related to a specific entity or concept

references to specific companies and organizations

No Comments

No Known Activations