INDEX

Explanations

references to dangerous substances or environmental hazards

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.03

1:0.02

2:0.08

3:0.19

4:0.03

5:0.04

6:0.11

7:0.19

8:0.04

9:0.05

10:0.07

11:0.10

Negative Logits

��

-1.85

��

-1.63

��

-1.45

ngth

-1.42

��

-1.35

�

-1.24

ername

-1.23

incial

-1.23

iqueness

-1.20

estinal

-1.19

POSITIVE LOGITS

 espresso

1.28

 fumes

1.21

 headlights

1.19

 haze

1.13

 windshield

1.13

 decomp

1.08

 propell

1.06

 Archdemon

1.04

 Divide

1.03

 inhal

1.02

Activations Density 0.006%

references to dangerous substances or environmental hazards

No Comments

No Known Activations