INDEX

Explanations

phrases indicating progression or development

oai_token-act-pair · gpt-3.5-turbo

references to challenges or experiences encountered on a journey

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

byter

-0.69

 Plex

-0.69

iple

-0.69

avorite

-0.68

itton

-0.68

 concess

-0.67

oubted

-0.66

olor

-0.66

 pecul

-0.66

 Flavoring

-0.64

POSITIVE LOGITS

ward

0.97

steps

0.83

WARD

0.78

finding

0.76

seeing

0.71

Step

0.70

umatic

0.70

agic

0.70

fare

0.69

forward

0.67

Activations Density 0.012%

phrases indicating progression or development

references to challenges or experiences encountered on a journey

No Comments

No Known Activations