INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals and entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 brakes

-0.74

abiding

-0.70

 notebooks

-0.70

stood

-0.68

 insidious

-0.67

 gems

-0.66

 deciding

-0.66

 abiding

-0.66

boards

-0.65

 apprentices

-0.64

POSITIVE LOGITS

utterstock

1.07

File

0.95

anie

0.91

lando

0.91

 Shutterstock

0.91

imedia

0.85

esa

0.84

HCR

0.83

Image

0.83

uart

0.83

Activations Density 0.075%

names of people

proper nouns, specifically names of individuals and entities

No Comments

No Known Activations