INDEX

Explanations

phrases related to blame and accountability

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

0:0.07

1:0.03

2:0.05

3:0.04

4:0.06

5:0.04

6:0.23

7:0.05

8:0.09

9:0.24

10:0.03

11:0.03

Negative Logits

 Gork

-4.21

Magikarp

-4.06

 Stones

-4.00

Tan

-3.87

Za

-3.79

 Droid

-3.67

 Tanaka

-3.64

 sshd

-3.63

 darts

-3.62

 fishes

-3.57

POSITIVE LOGITS

Charl

10.25

 Charlotte

10.14

 Charl

6.92

 Charleston

6.10

 Carol

6.04

CHAR

5.48

 Raleigh

5.45

 Caroline

5.44

 Carolina

5.43

 Cary

5.38

Activations Density 0.003%

phrases related to blame and accountability

No Comments

No Known Activations