INDEX

Explanations

the word "Being" followed by a descriptive phrase

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Being" 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

rez

-0.75

ummy

-0.74

="#

-0.73

ett

-0.71

ummies

-0.70

OUP

-0.69

Ã©s

-0.68

Ã¨re

-0.66

dress

-0.63

ombat

-0.63

POSITIVE LOGITS

©¶æ

0.80

 deprived

0.79

etheless

0.74

 reluct

0.71

 immersed

0.70

 intimidated

0.70

 exhausted

0.69

 unable

0.68

 minded

0.68

 able

0.68

Activations Density 0.065%

the word "Being" followed by a descriptive phrase

the presence of the word "Being" and its variations

No Comments

No Known Activations