INDEX

Explanations

keywords related to role-playing games

oai_token-act-pair · gpt-3.5-turbo

terms related to role-playing games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 seal

-0.62

 seals

-0.61

 recip

-0.60

 yield

-0.60

 Kirin

-0.60

 morning

-0.59

 Hydro

-0.59

sec

-0.59

 candid

-0.58

 hydrogen

-0.56

POSITIVE LOGITS

playing

4.05

played

3.14

plays

2.48

play

2.22

players

2.02

Playing

1.93

player

1.54

PLAY

1.52

 Playing

1.49

Play

1.34

Activations Density 0.011%

keywords related to role-playing games

terms related to role-playing games

No Comments

No Known Activations