INDEX

Explanations

phrases related to investigations 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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.11

1:0.04

2:0.16

3:0.14

4:0.11

5:0.08

6:0.03

7:0.06

8:0.03

9:0.12

10:0.04

11:0.03

Negative Logits

 Reeves

-3.04

 Rhodes

-2.93

SPONSORED

-2.67

 Petraeus

-2.45

 Hitchcock

-2.45

 Patt

-2.40

 Rudd

-2.39

 Dawkins

-2.37

 Marvin

-2.30

 …"

-2.29

POSITIVE LOGITS

�

4.63

�

4.10

�

4.01

ズ

3.98

†

3.73

§

3.71

�

3.60

�

3.56

�

3.55

��

3.51

Activations Density 0.256%

phrases related to investigations and accountability

No Comments

No Known Activations