INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĤ·ãĥ£

-0.73

Beck

-0.72

hardt

-0.67

adr

-0.67

IGH

-0.67

IFE

-0.63

arist

-0.62

omes

-0.62

 sorts

-0.61

UFF

-0.61

POSITIVE LOGITS

etsk

0.95

Pok

0.93

asus

0.93

oshenko

0.88

ongyang

0.86

atern

0.83

etry

0.82

ilon

0.77

gran

0.77

etary

0.77

Activations Density 0.042%

proper nouns

proper nouns, particularly names and places

No Comments

No Known Activations