INDEX

Explanations

top rankings or lists

oai_token-act-pair · gpt-3.5-turbo

references to ranking or listing items, particularly in a "Top" format

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

ufact

-0.75

 Gaul

-0.71

Äĩ

-0.69

riages

-0.64

 hunger

-0.64

BILITY

-0.63

 ascert

-0.63

vous

-0.63

 detachment

-0.63

ngth

-0.63

POSITIVE LOGITS

eka

1.08

Top

0.97

most

0.96

ographical

0.91

Top

0.88

top

0.86

ography

0.84

TOP

0.84

Tier

0.84

Boss

0.81

Activations Density 0.022%

top rankings or lists

references to ranking or listing items, particularly in a "Top" format

No Comments

No Known Activations