INDEX

Explanations

statements about non-responsiveness to requests or comments

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "did" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hog

-0.65

isu

-0.65

stood

-0.65

lined

-0.61

ãĤ´ãĥ³

-0.61

case

-0.61

heid

-0.60

worms

-0.60

fields

-0.60

liner

-0.59

POSITIVE LOGITS

actic

1.11

not

1.02

 indeed

1.01

pez

0.98

 manage

0.97

NOT

0.89

oms

0.87

zed

0.86

anos

0.85

ppel

0.84

Activations Density 0.109%

statements about non-responsiveness to requests or comments

instances of the verb "did" in various contexts

No Comments

No Known Activations