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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.07

10:0.08

11:0.06

Negative Logits

utic

-3.00

�

-2.95

etheless

-2.91

 experiences

-2.87

 Functions

-2.74

Lear

-2.66

liter

-2.53

itivity

-2.52

ensitivity

-2.47

eno

-2.43

POSITIVE LOGITS

jew

3.90

 UKIP

2.98

 trustee

2.94

 jewel

2.92

BBC

2.91

 Ukip

2.90

Jew

2.77

 Muller

2.76

ECB

2.73

mob

2.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.