INDEX

Explanations

phrases related to expectations or predictions

oai_token-act-pair · gpt-3.5-turbo

phrases that reference expectations or things that are anticipated to happen

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

agra

-0.76

aina

-0.73

tex

-0.71

 Rath

-0.70

wallet

-0.70

nan

-0.68

available

-0.68

tein

-0.68

fighting

-0.67

stein

-0.67

POSITIVE LOGITS

ICAL

0.77

ORY

0.75

 retribution

0.68

LY

0.67

IAL

0.65

EQU

0.64

OLOG

0.64

TRUMP

0.62

ĭ

0.62

wcs

0.62

Activations Density 0.028%

phrases related to expectations or predictions

phrases that reference expectations or things that are anticipated to happen

No Comments

No Known Activations