INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

2:0.08

3:0.09

4:0.09

5:0.07

6:0.09

7:0.08

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

etheless

-1.72

arten

-1.66

��

-1.56

 actionGroup

-1.54

MOR

-1.45

izations

-1.43

 Chomsky

-1.42

EMBER

-1.41

Dialogue

-1.39

APP

-1.36

POSITIVE LOGITS

jab

2.11

olson

1.60

cci

1.59

 mango

1.52

adeon

1.51

 paddle

1.50

apons

1.50

ibaba

1.49

lux

1.47

avis

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.