INDEX

Explanations

phrases related to horror or fear

oai_token-act-pair · gpt-3.5-turbo

references to the term "Horror."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•layer 6 - fear

No Comments

Negative Logits

anwhile

-0.81

ãģ¦

-0.79

0000000000000000

-0.71

ãģ®éŃĶ

-0.68

 succeeding

-0.67

ħĭ

-0.66

eer

-0.65

 timers

-0.63

 graded

-0.62

enhagen

-0.62

POSITIVE LOGITS

izontal

1.34

izont

1.31

izons

1.24

oscope

1.11

rible

1.09

izon

1.05

ribly

1.02

rors

1.01

ror

1.01

rid

0.95

Activations Density 0.031%

phrases related to horror or fear

references to the term "Horror."

No Comments

No Known Activations