INDEX

Explanations

terms related to significant changes or transformation

oai_token-act-pair · gpt-3.5-turbo

terms related to change and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

©¶æ

-0.74

senal

-0.64

 Illegal

-0.63

ItemTracker

-0.63

ãģ®å®

-0.62

 Penet

-0.62

mia

-0.62

 Borders

-0.62

Reloaded

-0.61

 piercing

-0.61

POSITIVE LOGITS

eless

0.99

ique

0.89

elight

0.88

ients

0.88

et

0.87

het

0.86

eness

0.86

engers

0.86

eto

0.85

er

0.85

Activations Density 0.019%

terms related to significant changes or transformation

terms related to change and transformation

No Comments

No Known Activations