INDEX

Explanations

mentions of bonuses or rewards

oai_token-act-pair · gpt-3.5-turbo

mentions of bonuses or rewards

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

tics

-0.86

scape

-0.80

ãĤ¢ãĥ«

-0.78

URES

-0.78

atters

-0.77

tic

-0.74

lÃ©

-0.74

turn

-0.72

ichen

-0.71

ŀ

-0.71

POSITIVE LOGITS

 bonus

1.21

 bonuses

1.08

 depreciation

0.95

 accrued

0.84

 Bonus

0.81

 indemn

0.81

 extras

0.79

Bonus

0.78

 parachute

0.77

 accol

0.76

Activations Density 0.015%

mentions of bonuses or rewards

mentions of bonuses or rewards

No Comments

No Known Activations