INDEX

Explanations

references to the United States (U.S.) or its related entities

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 STATS

-0.81

*/(

-0.73

theless

-0.72

errors

-0.64

 Shea

-0.64

ĵĺ

-0.64

bole

-0.62

 unpre

-0.58

tumblr

-0.57

DragonMagazine

-0.56

POSITIVE LOGITS

eal

0.85

.,

0.82

wan

0.82

ells

0.80

 Embassy

0.79

igma

0.78

.?

0.78

GI

0.78

ierra

0.77

ESSION

0.75

Activations Density 0.044%

references to the United States (U.S.) or its related entities

references to the United States

No Comments

No Known Activations