INDEX

Explanations

words related to confusion or frustration

oai_token-act-pair · gpt-3.5-turbo

past participles and gerunds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

dinand

-0.85

©¶æ

-0.80

itions

-0.76

irtual

-0.76

vernment

-0.74

 allowable

-0.70

 enriched

-0.70

assisted

-0.70

 refin

-0.70

 plural

-0.69

POSITIVE LOGITS

ly

0.82

Dak

0.81

 Shack

0.80

ingly

0.78

LY

0.77

 Dragonbound

0.76

 Barkley

0.75

iate

0.73

Toy

0.72

0.69

Activations Density 0.103%

words related to confusion or frustration

past participles and gerunds

No Comments

No Known Activations