INDEX

Explanations

No Explanations Found

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

0:0.07

1:0.06

2:0.08

3:0.08

4:0.07

5:0.06

6:0.08

7:0.08

8:0.08

9:0.09

10:0.10

11:0.07

Negative Logits

hess

-2.93

ertodd

-2.89

 archae

-2.57

 decorated

-2.56

 Zimmer

-2.55

 Wikimedia

-2.52

 Rove

-2.47

urion

-2.47

 decor

-2.44

PDF

-2.42

POSITIVE LOGITS

ESC

3.09

soDeliveryDate

2.96

psc

2.95

 Deliver

2.86

 Outbreak

2.79

 Falling

2.76

 Hunger

2.73

 Nightmares

2.72

RTX

2.72

 Sailor

2.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.