INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

tis

-1.56

TIT

-1.52

 Mortal

-1.50

 Runes

-1.38

dule

-1.35

aired

-1.35

screen

-1.35

ノ

-1.34

WR

-1.32

Combat

-1.32

POSITIVE LOGITS

psey

1.58

fman

1.57

 anecd

1.57

coh

1.52

ijing

1.51

DonaldTrump

1.50

ertodd

1.50

CVE

1.47

 pseudonym

1.46

 Bernstein

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.