INDEX

Explanations

phrases related to the term "Monster"

oai_token-act-pair · gpt-3.5-turbo

references to the "Monster Hunter" franchise

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

SourceFile

-0.90

ories

-0.81

atories

-0.78

ndra

-0.73

issance

-0.73

choes

-0.71

nee

-0.71

ynski

-0.71

grad

-0.70

nington

-0.69

POSITIVE LOGITS

 monsters

0.88

 beasts

0.88

 monster

0.80

 hunter

0.79

wre

0.79

 hunts

0.77

 Monstrous

0.75

 Monsters

0.74

 bite

0.74

 hunt

0.73

Activations Density 0.032%

phrases related to the term "Monster"

references to the "Monster Hunter" franchise

No Comments

No Known Activations