INDEX

Explanations

instances of the word "Shar" followed by a number (e.g., Shar9, Shar10)

oai_token-act-pair · gpt-3.5-turbo

references to Sharia law and related legal systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĸļ

-0.73

 Europa

-0.71

ortium

-0.71

 Dangerous

-0.69

vironment

-0.66

 Hawaiian

-0.65

ALS

-0.64

 Uran

-0.63

é¾įå¥ĳå£«

-0.63

ATS

-0.62

POSITIVE LOGITS

pton

1.12

ples

1.07

ãĥ£

1.06

pling

0.99

pless

0.98

ning

0.93

quet

0.90

jah

0.88

pering

0.86

pen

0.85

Activations Density 0.010%

instances of the word "Shar" followed by a number (e.g., Shar9, Shar10)

references to Sharia law and related legal systems

No Comments

No Known Activations