INDEX

Explanations

proper nouns, specifically names related to people or places

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jaroslav" or variations of it

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

ĨĴ

-0.76

 Samoa

-0.74

ãģį

-0.74

ancial

-0.73

EPA

-0.69

ORE

-0.69

imity

-0.69

 Canterbury

-0.66

phis

-0.66

acebook

-0.66

POSITIVE LOGITS

Jar

1.30

Jar

1.25

jar

0.93

Ã³n

0.93

assic

0.93

rod

0.92

 jars

0.91

abul

0.86

acca

0.84

jar

0.83

Activations Density 0.004%

proper nouns, specifically names related to people or places

mentions of the name "Jaroslav" or variations of it

No Comments

No Known Activations