INDEX

Explanations

proper names, specifically first names like "Ivan" and "Igor."

oai_token-act-pair · gpt-3.5-turbo

names of individuals, particularly those starting with "Ivan" or "Igor."

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

Score

-0.74

aver

-0.69

reads

-0.68

inals

-0.67

Scient

-0.65

Gameplay

-0.65

ĻĤ

-0.64

Americans

-0.63

woman

-0.63

Methods

-0.62

POSITIVE LOGITS

ovich

1.15

 Ivan

1.06

hoe

1.01

ovic

0.93

opol

0.92

ova

0.77

imov

0.76

stadt

0.76

Ily

0.75

Äį

0.75

Activations Density 0.012%

proper names, specifically first names like "Ivan" and "Igor."

names of individuals, particularly those starting with "Ivan" or "Igor."

No Comments

No Known Activations