INDEX

Explanations

commands or imperatives in text

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_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.7.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

1:0.08

2:0.08

3:0.10

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.06

Negative Logits

phabet

-2.65

vernment

-2.64

 actionGroup

-2.43

partisan

-2.42

andom

-2.38

population

-2.36

oyal

-2.35

incial

-2.35

parency

-2.29

VIDIA

-2.27

POSITIVE LOGITS

 Horowitz

2.22

 postp

2.18

OK

2.10

 argued

2.08

 accidentally

2.02

 Butt

2.02

Kuh

2.01

SQ

1.99

 Coffin

1.95

Fig

1.92

Activations Density 0.000%

commands or imperatives in text

No Comments

No Known Activations