INDEX

Explanations

phrases indicating a high frequency or repetition of events

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the frequency of occurrences or behaviors

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

ortium

-0.98

ufact

-0.82

agra

-0.76

ĪĴ

-0.72

tty

-0.69

opol

-0.69

dinand

-0.68

yright

-0.67

arat

-0.67

arnaev

-0.66

POSITIVE LOGITS

ago

0.75

nir

0.73

é¾įå

0.71

 when

0.71

 consuming

0.71

interstitial

0.69

ilies

0.67

Ago

0.67

entimes

0.67

frames

0.66

Activations Density 0.024%

phrases indicating a high frequency or repetition of events

phrases emphasizing the frequency of occurrences or behaviors

No Comments

No Known Activations