INDEX

Explanations

mentions of estimations or value amounts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "est" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

gb

-0.84

Õ

-0.81

Beh

-0.76

ãĤ§

-0.75

ãĥ´ãĤ¡

-0.72

beit

-0.71

hands

-0.70

veyard

-0.69

äºĶ

-0.68

llah

-0.68

POSITIVE LOGITS

est

1.21

uary

0.97

hetics

0.86

imate

0.83

 simultane

0.75

hetically

0.73

rator

0.73

rant

0.72

ophe

0.71

ript

0.71

Activations Density 0.004%

mentions of estimations or value amounts

occurrences of the word "est" in various contexts

No Comments

No Known Activations