INDEX

Explanations

references to bonuses and rewards in a financial or incentive context

oai_token-act-pair · gpt-3.5-turbo

references to bonuses and rewards

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

ãĤ¢ãĥ«

-0.87

tics

-0.82

scape

-0.80

apest

-0.79

turn

-0.74

alter

-0.73

ichen

-0.72

atters

-0.72

lÃ©

-0.72

Ö¼

-0.72

POSITIVE LOGITS

 bonus

1.11

 depreciation

0.91

 bonuses

0.90

 accrued

0.88

Reviewer

0.81

 athlet

0.80

 parachute

0.77

 extras

0.76

 payout

0.76

 incentive

0.74

Activations Density 0.020%

references to bonuses and rewards in a financial or incentive context

references to bonuses and rewards

No Comments

No Known Activations