INDEX

Explanations

references to specific locations or cities

oai_token-act-pair · gpt-3.5-turbo

mentions of geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

*/(

-0.84

 Cosponsors

-0.84

amount

-0.78

ertodd

-0.77

>(

-0.76

wcs

-0.75

imei

-0.71

 showc

-0.71

 incent

-0.70

Reviewer

-0.69

POSITIVE LOGITS

 course

0.91

 Nations

0.78

 Towns

0.73

 southwestern

0.72

 Mour

0.71

 northern

0.70

 Northern

0.70

 southern

0.70

 Yemen

0.69

 Refuge

0.69

Activations Density 0.398%

references to specific locations or cities

mentions of geographical locations

No Comments

No Known Activations