INDEX

Explanations

conditional statements involving potential consequences

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.03

2:0.06

3:0.10

4:0.09

5:0.09

6:0.07

7:0.03

8:0.08

9:0.21

10:0.08

11:0.04

Negative Logits

 ASAP

-1.36

NBA

-1.28

Tonight

-1.19

Chel

-1.12

 Indies

-1.09

 Schedule

-1.09

oodle

-1.07

 INCLUD

-1.05

 Ahead

-1.03

Tomorrow

-1.03

POSITIVE LOGITS

 Conan

1.25

 Alter

1.24

ICLE

1.05

 Sullivan

1.05

Mag

1.04

 Representative

1.02

ONSORED

1.01

 Cantor

0.98

 Kessler

0.98

 Petty

0.97

Activations Density 0.014%

conditional statements involving potential consequences

No Comments

No Known Activations