INDEX

Explanations

phrases related to making decisions or having control/power over something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "up" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CLSID

-0.81

-0.70

VICE

-0.66

ATA

-0.61

 separation

-0.60

 Beijing

-0.56

 Fidel

-0.56

gee

-0.56

]"

-0.56

 Barnett

-0.55

POSITIVE LOGITS

rated

1.06

orthy

0.96

erd

0.95

raised

0.89

ended

0.85

regulated

0.82

grading

0.79

swing

0.78

riter

0.77

draft

0.77

Activations Density 0.046%

phrases related to making decisions or having control/power over something

instances of the word "up" used in various contexts

No Comments

No Known Activations