INDEX

Explanations

references to mana in a gaming context

oai_token-act-pair · gpt-3.5-turbo

terms related to game mechanics, particularly those involving mana and stamina

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

eering

-0.73

Boe

-0.73

 Murdoch

-0.71

enegger

-0.71

iets

-0.71

ettings

-0.70

angers

-0.69

person

-0.68

IAL

-0.68

FW

-0.67

POSITIVE LOGITS

veyard

0.89

forth

0.74

ASE

0.70

 exhaustion

0.69

 depletion

0.69

conservancy

0.68

 ILCS

0.68

pl

0.68

 mana

0.68

 Sabha

0.68

Activations Density 0.012%

references to mana in a gaming context

terms related to game mechanics, particularly those involving mana and stamina

No Comments

No Known Activations