INDEX

Explanations

the word "Lie" with various capitalizations and word combinations containing it

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lie" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

orsi

-0.70

iles

-0.70

 nomine

-0.69

iaries

-0.68

AVG

-0.68

ISO

-0.66

ILE

-0.64

ivari

-0.64

iless

-0.62

âĶģ

-0.61

POSITIVE LOGITS

utenant

1.29

uten

1.23

 detector

1.18

ge

0.96

berman

0.96

bling

0.88

glers

0.87

 detectors

0.86

bler

0.81

 dormant

0.81

Activations Density 0.030%

the word "Lie" with various capitalizations and word combinations containing it

occurrences of the word "lie" in various contexts

No Comments

No Known Activations