INDEX

Explanations

elements related to character attributes and abilities in a role-playing game

oai_token-act-pair · gpt-3.5-turbo

terms related to character abilities and attributes in a role-playing game context

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

JO

-0.76

DJ

-0.74

JA

-0.69

flies

-0.68

LH

-0.67

HL

-0.66

liga

-0.65

ettel

-0.65

Ò

-0.65

POSITIVE LOGITS

 Dexterity

1.07

 Arcane

1.05

 Charisma

1.01

 sorcerer

1.01

nec

0.98

 cleric

0.96

spell

0.89

 arcane

0.89

 caster

0.87

 Spell

0.86

Activations Density 0.169%

elements related to character attributes and abilities in a role-playing game

terms related to character abilities and attributes in a role-playing game context

No Comments

No Known Activations