INDEX

Explanations

references to PvP (player versus player) and PvE (player versus environment) content in a gaming context

oai_token-act-pair · gpt-3.5-turbo

references to player versus environment (PvE) game mechanics and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

apter

-0.82

uate

-0.81

oux

-0.77

ulous

-0.73

ulously

-0.72

è£ħ

-0.68

ãĥ³ãĤ¸

-0.68

undown

-0.67

åĭ

-0.66

ault

-0.65

POSITIVE LOGITS

Pv

0.91

tp

0.82

lege

0.80

zees

0.74

ech

0.74

lyak

0.73

erver

0.71

erest

0.71

robe

0.69

pperc

0.69

Activations Density 0.033%

references to PvP (player versus player) and PvE (player versus environment) content in a gaming context

references to player versus environment (PvE) game mechanics and related terminology

No Comments

No Known Activations