INDEX

Explanations

details about recent discoveries or findings

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "discovered"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cussion

-0.75

 paced

-0.75

quote

-0.73

yip

-0.72

annis

-0.71

cise

-0.71

wr

-0.69

adra

-0.66

wrap

-0.65

req

-0.65

POSITIVE LOGITS

Ô

0.99

gdala

0.85

çīĪ

0.78

ibility

0.75

ãĤ¼

0.72

Frameworks

0.72

 Primordial

0.72

ä½¿

0.69

Leaks

0.69

Discover

0.68

Activations Density 0.025%

details about recent discoveries or findings

occurrences of the word "discovered"

No Comments

No Known Activations