INDEX

Explanations

words related to Greece

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ree"

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

enegger

-0.93

 Mongolia

-0.72

 specificity

-0.70

inelli

-0.68

ancial

-0.67

ictive

-0.66

ulators

-0.64

rift

-0.64

 Takeru

-0.63

 Manson

-0.62

POSITIVE LOGITS

pee

0.98

pees

0.94

bling

0.89

ks

0.89

ce

0.86

cker

0.85

bles

0.84

glas

0.84

llor

0.79

ree

0.79

Activations Density 0.020%

words related to Greece

occurrences of the substring "ree"

No Comments

No Known Activations