INDEX

Explanations

words related to locations or places

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "est" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

gb

-0.82

ãĥ´ãĤ¡

-0.75

llah

-0.73

ãĤ§

-0.72

Berry

-0.72

Õ

-0.71

hands

-0.69

Shot

-0.69

jee

-0.66

Beh

-0.65

POSITIVE LOGITS

est

1.41

uary

0.88

 simultane

0.85

imate

0.80

hetics

0.79

 seiz

0.74

hetically

0.73

 lapt

0.72

rator

0.71

 COUR

0.69

Activations Density 0.006%

words related to locations or places

occurrences of the word "est" and its variations in different contexts

No Comments

No Known Activations