INDEX

Explanations

words related to a specific video game series, particularly "Elder Scrolls" and "Skyrim"

oai_token-act-pair · gpt-3.5-turbo

references to video game titles and franchises, particularly those related to "Elder Scrolls."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

nels

-0.69

ACTION

-0.68

abwe

-0.67

eli

-0.66

cation

-0.66

hillary

-0.66

clusions

-0.64

berman

-0.64

Qual

-0.63

ted

-0.63

POSITIVE LOGITS

 Scrolls

1.13

 Magicka

0.84

 Shards

0.78

 Uriel

0.78

 Trilogy

0.77

âĶĢ

0.76

 scrolls

0.75

 Shard

0.74

 Mysteries

0.74

 Scroll

0.74

Activations Density 0.021%

words related to a specific video game series, particularly "Elder Scrolls" and "Skyrim"

references to video game titles and franchises, particularly those related to "Elder Scrolls."

No Comments

No Known Activations