INDEX

Explanations

proper nouns related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

place names or national identifiers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LCS

-0.64

bye

-0.63

ffen

-0.58

ffe

-0.58

pling

-0.55

 Âł Âł Âł Âł

-0.55

 threaded

-0.54

 conscience

-0.54

ptr

-0.54

houses

-0.53

POSITIVE LOGITS

ians

2.57

ian

2.51

ias

1.56

ienne

1.55

iana

1.47

ia

1.44

IAN

1.43

ien

1.42

arian

1.39

ican

1.30

Activations Density 0.092%

proper nouns related to geographical locations

place names or national identifiers

No Comments

No Known Activations