INDEX

Explanations

phrases indicating that something is "not new"

oai_token-act-pair · gpt-3.5-turbo

the concept of something being new or not new

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ignt

-0.75

 PRESS

-0.73

weeney

-0.68

chance

-0.68

 teasp

-0.67

 sqor

-0.65

thora

-0.65

++++

-0.64

ombies

-0.64

afia

-0.63

POSITIVE LOGITS

bie

1.07

bies

0.94

yk

0.79

Reilly

0.77

 colonialism

0.74

 beginnings

0.73

 Zealand

0.73

 arrivals

0.73

born

0.72

rums

0.71

Activations Density 0.057%

phrases indicating that something is "not new"

the concept of something being new or not new

No Comments

No Known Activations