INDEX

Explanations

mentions of geographical locations, specifically states in the United States

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "state" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

alore

-0.74

 elbows

-0.68

 subp

-0.67

inges

-0.66

 tremend

-0.66

 cumbers

-0.65

utenberg

-0.65

 pitch

-0.65

anos

-0.65

 dime

-0.65

POSITIVE LOGITS

tenance

1.25

theless

1.00

ruction

0.84

ãĥĥ

0.82

ãĤ£

0.78

TextColor

0.78

Pierre

0.78

lihood

0.78

vier

0.77

strument

0.76

Activations Density 0.059%

mentions of geographical locations, specifically states in the United States

mentions of the term "state" in various contexts

No Comments

No Known Activations