INDEX

Explanations

mentions of environmental hazards and toxic substances

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.01

2:0.12

3:0.17

4:0.04

5:0.29

6:0.03

7:0.05

8:0.06

9:0.02

10:0.05

11:0.02

Negative Logits

 Recover

-1.80

 Conservation

-1.74

 decriminal

-1.68

 unravel

-1.61

 Detection

-1.59

覚醒

-1.57

 conservation

-1.55

 Prohibition

-1.54

 rescuing

-1.53

 dispens

-1.52

POSITIVE LOGITS

 Xbox

1.88

 locker

1.73

 videog

1.71

Kot

1.63

 fixtures

1.63

 uniforms

1.61

ikarp

1.59

Games

1.58

 games

1.57

Rio

1.56

Activations Density 0.895%

mentions of environmental hazards and toxic substances

No Comments

No Known Activations