INDEX

Explanations

phrases related to responses or reactions

oai_token-act-pair · gpt-3.5-turbo

phrases that discuss responses or reactions, particularly in contexts of debate or argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Quran

-0.69

 Replay

-0.63

 UNCLASSIFIED

-0.62

 Koran

-0.61

oster

-0.61

 Grateful

-0.59

 foreigner

-0.59

ãĥīãĥ©ãĤ´ãĥ³

-0.58

"},"

-0.57

 Fifa

-0.57

POSITIVE LOGITS

trak

0.83

aque

0.75

arser

0.72

cock

0.71

addon

0.69

ipel

0.69

iliated

0.69

emetery

0.68

heric

0.68

ayers

0.68

Activations Density 0.564%

phrases related to responses or reactions

phrases that discuss responses or reactions, particularly in contexts of debate or argument

No Comments

No Known Activations