INDEX

Explanations

words in a non-Latin script, possibly Cyrillic

oai_token-act-pair · gpt-3.5-turbo

characters or symbols, potentially indicating special or foreign textual elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 manif

-0.67

 dolls

-0.65

 Riley

-0.65

 conduc

-0.64

 temptation

-0.64

 visitation

-0.64

ktop

-0.64

bourg

-0.64

enegger

-0.61

 caravan

-0.61

POSITIVE LOGITS

Ð¾Ð

1.08

Ðµ

1.04

ÑĢ

1.04

¬

1.04

Į

1.03

°

1.02

Ĺ

1.00

ĺ

1.00

Ñĥ

0.99

¹

0.99

Activations Density 0.051%

words in a non-Latin script, possibly Cyrillic

characters or symbols, potentially indicating special or foreign textual elements

No Comments

No Known Activations