INDEX

Explanations

references to shipping or shipping-related terms

oai_token-act-pair · gpt-3.5-turbo

references to shipping logistics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

si

-0.83

ktop

-0.76

nered

-0.73

ellen

-0.71

nos

-0.70

eds

-0.70

opes

-0.70

gee

-0.69

enhagen

-0.68

bre

-0.67

POSITIVE LOGITS

 shipping

0.89

 containers

0.87

 container

0.80

 Yamato

0.78

 Shipping

0.77

 shipped

0.72

 transported

0.70

HAM

0.70

Ship

0.69

wreck

0.68

Activations Density 0.017%

references to shipping or shipping-related terms

references to shipping logistics

No Comments

No Known Activations