INDEX

Explanations

references to the Quran

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

0:0.08

1:0.07

2:0.07

3:0.10

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.10

Negative Logits

.--

-3.45

¨

-3.11

keyes

-2.86

.","

-2.74

................

-2.72

●

-2.70

 Attacks

-2.67

■

-2.66

.—

-2.63

 START

-2.58

POSITIVE LOGITS

alsa

3.05

aque

2.61

MRI

2.50

 Fifa

2.40

Audio

2.40

Reference

2.40

VICE

2.39

 Mali

2.33

 sparse

2.33

dfx

2.31

Activations Density 0.000%

references to the Quran

No Comments

No Known Activations