INDEX

Explanations

statements indicating something has never been experienced or seen before

oai_token-act-pair · gpt-3.5-turbo

expressions of experiences or situations that have never happened before

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

States

-0.66

VL

-0.62

href

-0.62

uing

-0.60

estate

-0.59

 Archive

-0.57

 Affordable

-0.56

 Restoration

-0.56

 Towards

-0.55

 Journals

-0.55

POSITIVE LOGITS

 been

1.34

been

1.33

theless

1.18

 Been

1.09

 heard

1.08

 gotten

1.07

 tasted

1.06

 existed

1.00

 seen

0.98

 interacted

0.96

Activations Density 0.040%

statements indicating something has never been experienced or seen before

expressions of experiences or situations that have never happened before

No Comments

No Known Activations