INDEX

Explanations

years signaling specific dates or periods in history

oai_token-act-pair · gpt-3.5-turbo

references to specific years in the 1800s

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

Not in Any Lists

No Comments

Negative Logits

acci

-0.91

paralle

-0.78

colo

-0.78

enegger

-0.76

atri

-0.75

notation

-0.74

glas

-0.73

alez

-0.73

ringe

-0.71

algia

-0.71

POSITIVE LOGITS

sie

0.85

sburg

0.79

hrs

0.75

0.73

0.71

0.69

 Hots

0.67

ãĤ¼ãĤ¦ãĤ¹

0.65

0.64

Activations Density 0.036%

years signaling specific dates or periods in history

references to specific years in the 1800s

No Comments

No Known Activations