INDEX

Explanations

technical or scientific terminology related to processes and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 challeng

-0.77

 showc

-0.75

 misunder

-0.73

 whisk

-0.71

orem

-0.70

nings

-0.68

abee

-0.67

mes

-0.66

 pestic

-0.66

tails

-0.66

POSITIVE LOGITS

llor

0.94

unia

0.80

ropolitan

0.80

é¾įå¥ĳå£«

0.77

elaide

0.75

èĢħ

0.72

 Century

0.71

ãĥīãĥ©ãĤ´ãĥ³

0.69

 Heights

0.69

utical

0.67

Activations Density 0.033%

technical or scientific terminology related to processes and classifications

No Comments

No Known Activations