INDEX

Explanations

proper nouns, particularly names of people and places

oai_token-act-pair · gpt-3.5-turbo

references to individuals with the last name "Mayer."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ity

-0.83

ious

-0.71

ibly

-0.70

ibility

-0.70

etition

-0.69

ile

-0.69

reme

-0.67

nel

-0.67

itri

-0.66

nik

-0.66

POSITIVE LOGITS

assetsadobe

0.75

iquid

0.69

hof

0.68

_>

0.65

haps

0.65

////////////////

0.65

-+-+-+-+

0.64

renheit

0.64

wood

0.64

doms

0.63

Activations Density 0.052%

proper nouns, particularly names of people and places

references to individuals with the last name "Mayer."

No Known Activations