INDEX

Explanations

occurrences of a specific word: "Where"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Where."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 roller

-0.70

ATURE

-0.67

)].

-0.66

astics

-0.64

 absorbing

-0.63

 digest

-0.62

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.62

apt

-0.61

 secretion

-0.61

 Doctrine

-0.61

POSITIVE LOGITS

abouts

1.45

upon

1.29

fore

1.20

soever

1.15

ver

0.99

verages

0.80

onga

0.79

acan

0.78

 else

0.76

ĪĴ

0.71

Activations Density 0.034%

occurrences of a specific word: "Where"

occurrences of the word "Where."

No Comments

No Known Activations