INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

and signal occurrences of the character "ľ"

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

 condem

-0.79

 apes

-0.69

 Norn

-0.68

 reflex

-0.67

raints

-0.66

 purpose

-0.64

 Patriarch

-0.63

 disadvant

-0.63

 gist

-0.63

 deed

-0.62

POSITIVE LOGITS

ï¸ı

1.29

âĶĢâĶĢ

1.09

ternity

0.96

0.89

âĸł

0.88

Â°

0.86

jj

0.85

\-

0.84

conom

0.84

Â·Â·

0.84

Activations Density 0.269%

proper nouns or names

and signal occurrences of the character "ľ"

No Comments

No Known Activations