INDEX

Explanations

mentions of locations or settings near bodies of water

oai_token-act-pair · gpt-3.5-turbo

references to "seas" or related bodies of water

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

gee

-0.79

JECT

-0.65

IVES

-0.64

CTV

-0.64

 booth

-0.63

IO

-0.61

NC

-0.60

nce

-0.59

ACP

-0.59

Marginal

-0.59

POSITIVE LOGITS

 Seas

1.21

 seas

1.06

hell

1.02

boat

0.90

 Ocean

0.88

 Islands

0.85

 oceans

0.82

 shores

0.81

 unlaw

0.80

 waters

0.80

Activations Density 0.006%

mentions of locations or settings near bodies of water

references to "seas" or related bodies of water

No Comments

No Known Activations