INDEX

Explanations

references to the word "ok" with varying levels of emphasis

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ok."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

bugs

-0.70

lav

-0.66

oire

-0.65

ONSORED

-0.65

WHERE

-0.64

icone

-0.64

Arcade

-0.63

 Agric

-0.63

natureconservancy

-0.62

 missionaries

-0.62

POSITIVE LOGITS

lahoma

1.05

unin

1.03

lass

0.98

ettle

0.94

awaru

0.92

nown

0.92

aido

0.86

ernel

0.86

itty

0.86

owski

0.85

Activations Density 0.027%

references to the word "ok" with varying levels of emphasis

instances of the word "ok."

No Comments

No Known Activations