INDEX

Explanations

action words related to unlocking or achieving something

oai_token-act-pair · gpt-3.5-turbo

phrases related to unlocking achievements and game features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

annis

-0.72

ogram

-0.70

 Ferdinand

-0.66

nian

-0.64

ograms

-0.63

 Municip

-0.62

cas

-0.62

geist

-0.62

 Bombay

-0.61

hel

-0.61

POSITIVE LOGITS

 unlocking

0.91

 unlock

0.87

 unlocked

0.86

 unlocks

0.85

 Unlock

0.84

 recess

0.83

ESCO

0.82

ibility

0.81

ilings

0.79

 secrets

0.78

Activations Density 0.025%

action words related to unlocking or achieving something

phrases related to unlocking achievements and game features

No Comments

No Known Activations