INDEX

Explanations

references to the term "Bot."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "bot" and its variations

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

dress

-0.78

mble

-0.70

PLIED

-0.68

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.67

 Trib

-0.66

unm

-0.63

edly

-0.62

journal

-0.59

vironment

-0.58

-+

-0.57

POSITIVE LOGITS

anical

1.27

ania

1.06

anic

1.03

rol

0.96

any

0.95

anie

0.93

zeb

0.92

roph

0.92

wana

0.90

anus

0.89

Activations Density 0.019%

references to the term "Bot."

occurrences of the word "bot" and its variations

No Comments

No Known Activations