INDEX

Explanations

capitalized words related to specific locations or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns or capitalized terms related to specific entities or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.69

é¾įå¥ĳå£«

-0.67

 effic

-0.66

 nomine

-0.66

 related

-0.65

 suited

-0.64

 correct

-0.64

 wise

-0.63

 coupled

-0.63

 permitting

-0.62

POSITIVE LOGITS

isan

0.99

ipers

0.94

ieties

0.91

airs

0.90

itudes

0.90

idays

0.90

ombat

0.89

plet

0.86

arters

0.85

clerosis

0.84

Activations Density 0.249%

capitalized words related to specific locations or organizations

proper nouns or capitalized terms related to specific entities or concepts

No Comments

No Known Activations