INDEX

Explanations

proper nouns and institutions

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 stricken

-0.72

 unmatched

-0.71

isSpecialOrderable

-0.68

 weakest

-0.65

 forgiven

-0.63

 unrecogn

-0.63

 preached

-0.62

 psychiat

-0.62

 unresolved

-0.61

 toget

-0.61

POSITIVE LOGITS

photos

1.03

 Shutterstock

1.01

 Archives

1.00

 IMAGES

0.99

ulton

0.96

 screenshot

0.94

Images

0.92

)/

0.92

 Photography

0.90

 Images

0.90

Activations Density 0.217%

proper nouns and institutions

references to specific organizations and institutions

No Comments

No Known Activations