INDEX

Explanations

terms related to specific proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to organizations, structures, or notable entities

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

Ô

-0.86

terday

-0.81

 guiActiveUn

-0.74

 weap

-0.74

 simultane

-0.74

inventoryQuantity

-0.72

é¾įå¥ĳå£«

-0.72

-0.71

 matt

-0.69

assetsadobe

-0.69

POSITIVE LOGITS

iest

0.92

liest

0.77

osphere

0.76

ariat

0.75

est

0.75

hest

0.75

isher

0.74

agame

0.74

venth

0.73

isphere

0.73

Activations Density 0.278%

terms related to specific proper nouns or names

specific names or terms related to organizations, structures, or notable entities

No Comments

No Known Activations