INDEX

Explanations

terms related to the video game "Monster Hunter."

oai_token-act-pair · gpt-3.5-turbo

references to the "Monster" franchise and its related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atories

-0.92

ories

-0.83

SourceFile

-0.77

atche

-0.77

rup

-0.71

atory

-0.71

ynski

-0.70

ndra

-0.70

dated

-0.70

orship

-0.69

POSITIVE LOGITS

 beasts

0.81

wre

0.78

 Reborn

0.77

 Summon

0.76

 monsters

0.76

 Mash

0.71

busters

0.71

 vomit

0.71

ãĥĢ

0.71

 Fenrir

0.71

Activations Density 0.034%

terms related to the video game "Monster Hunter."

references to the "Monster" franchise and its related content

No Comments

No Known Activations