INDEX

Explanations

items listed numerically or categorically

oai_token-act-pair · gpt-3.5-turbo

references to lists, particularly in the context of enumerating items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 irrigation

-0.63

 overtime

-0.63

 daylight

-0.61

gy

-0.61

 tears

-0.60

 fertil

-0.60

sew

-0.59

 inclined

-0.59

 Strikes

-0.59

 circumcised

-0.57

POSITIVE LOGITS

list

4.15

lists

3.05

LIST

2.72

listed

2.30

List

2.30

 LIST

2.22

 List

2.21

 list

2.03

 Lists

1.88

 lists

1.68

Activations Density 0.018%

items listed numerically or categorically

references to lists, particularly in the context of enumerating items or concepts

No Comments

No Known Activations