INDEX

Explanations

MMORPG-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of specific terms related to MMORPGs

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

swick

-0.82

ãĥ´ãĤ¡

-0.79

 Coul

-0.78

 McCartney

-0.77

ku

-0.75

hold

-0.73

choes

-0.70

drawn

-0.68

ulkan

-0.67

angered

-0.66

POSITIVE LOGITS

ORPG

1.95

QB

1.02

FG

0.94

MM

0.94

achine

0.91

ategory

0.87

ONEY

0.84

ITH

0.82

TP

0.77

ajor

0.73

Activations Density 0.015%

MMORPG-related terms

mentions of specific terms related to MMORPGs

No Comments

No Known Activations