INDEX

Explanations

references to a specific geographic location

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Northern."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

inventoryQuantity

-0.93

verb

-0.87

earance

-0.84

awaru

-0.81

ulative

-0.80

utenberg

-0.79

inger

-0.78

ATURE

-0.78

endi

-0.77

enger

-0.76

POSITIVE LOGITS

 Hemisphere

1.26

 hemisphere

1.13

 Lights

1.01

 Territory

0.94

 Ireland

0.94

 Liberties

0.94

 Caucasus

0.89

most

0.83

 Isles

0.79

 Territories

0.79

Activations Density 0.023%

references to a specific geographic location

mentions of the word "Northern."

No Comments

No Known Activations