INDEX

Explanations

proper nouns with the last syllable "ner"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 DRAG

-0.74

 Haram

-0.74

CPI

-0.66

 risen

-0.64

 aliases

-0.62

sea

-0.60

 Skies

-0.59

Zh

-0.59

 Silk

-0.59

 Peaks

-0.59

POSITIVE LOGITS

ner

4.44

ners

2.85

NER

2.76

nery

1.89

ning

1.81

nings

1.54

ener

1.42

nered

1.37

nar

1.34

ned

1.23

Activations Density 0.021%

proper nouns with the last syllable "ner"

mentions of specific individuals or entities

No Comments

No Known Activations