INDEX

Explanations

questions and expressions of uncertainty

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

0:0.06

1:0.03

2:0.44

3:0.09

4:0.04

5:0.06

6:0.03

7:0.05

8:0.03

9:0.02

10:0.07

11:0.02

Negative Logits

Clean

-2.47

 cleaned

-2.36

 servicing

-2.35

Assembly

-2.32

ISO

-2.30

ofi

-2.16

 ILCS

-2.15

 accredited

-2.07

ISO

-2.06

atel

-2.05

POSITIVE LOGITS

 explanations

4.54

 explanation

4.45

 reasons

4.22

Reason

3.99

 answers

3.85

why

3.85

 explain

3.81

 reason

3.75

 Explan

3.74

WHY

3.72

Activations Density 0.321%

questions and expressions of uncertainty

No Comments

No Known Activations