INDEX

Explanations

descriptions of color and patterns in moths

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

0:0.15

1:0.03

2:0.14

3:0.16

4:0.07

5:0.14

6:0.04

7:0.08

8:0.03

9:0.02

10:0.05

11:0.03

Negative Logits

hower

-1.98

 Safe

-1.84

Deal

-1.77

nesday

-1.73

 scheduling

-1.70

ettings

-1.70

Weather

-1.68

 Gamble

-1.68

 lockdown

-1.68

 Shutdown

-1.67

POSITIVE LOGITS

 protr

2.99

 claws

2.57

 elong

2.57

shaped

2.40

 flesh

2.37

 dorsal

2.37

 brist

2.35

 membr

2.34

 curved

2.29

 ribs

2.26

Activations Density 0.334%

descriptions of color and patterns in moths

No Comments

No Known Activations