INDEX

Explanations

No Explanations Found

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

0:0.08

1:0.08

2:0.09

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

 Hindi

-2.65

 Incarn

-2.57

:"

-2.52

 Hannity

-2.52

 FOIA

-2.50

 Hopkins

-2.45

 Bihar

-2.45

 Allaah

-2.41

Jenn

-2.37

 Hicks

-2.37

POSITIVE LOGITS

entin

3.18

uble

2.88

abb

2.55

arant

2.44

ificant

2.40

ugu

2.38

overe

2.29

bsp

2.29

onga

2.29

oug

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.