INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

actionDate

-0.77

Interstitial

-0.76

qqa

-0.76

olphins

-0.72

ointed

-0.70

bsp

-0.66

yout

-0.65

×Ļ×

-0.65

division

-0.65

Effective

-0.65

POSITIVE LOGITS

 Weasley

1.04

's

0.86

 Wilde

0.84

 remembers

0.82

 loved

0.81

 knows

0.78

 realizes

0.77

 loves

0.77

 kissed

0.76

Doe

0.76

Activations Density 0.164%

proper nouns

proper nouns, specifically names of people

No Comments

No Known Activations