INDEX

Explanations

phrases related to rankings or top lists

oai_token-act-pair · gpt-3.5-turbo

references to ranking systems or lists

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

ufact

-0.71

 Gaul

-0.70

BILITY

-0.64

Äĩ

-0.63

riages

-0.63

 Advent

-0.62

 warr

-0.62

 enqu

-0.61

=~=~

-0.61

udence

-0.60

POSITIVE LOGITS

eka

1.00

most

1.00

Top

0.99

ographical

0.97

Top

0.91

top

0.91

TOP

0.87

iary

0.84

ography

0.83

ographies

0.82

Activations Density 0.008%

phrases related to rankings or top lists

references to ranking systems or lists

No Comments

No Known Activations