INDEX

Explanations

terms related to exploration and pioneers

oai_token-act-pair · gpt-3.5-turbo

references to explorers and exploration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lined

-0.76

uate

-0.75

cpu

-0.71

ueller

-0.71

rooms

-0.71

corn

-0.70

andra

-0.69

ilion

-0.68

fix

-0.68

ogyn

-0.67

POSITIVE LOGITS

 explorers

1.12

 expedition

1.09

 explorer

1.06

 adventurer

1.00

 Expedition

0.98

voy

0.92

 jour

0.92

 canoe

0.89

 journeys

0.88

 trek

0.88

Activations Density 0.104%

terms related to exploration and pioneers

references to explorers and exploration

No Comments

No Known Activations