INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

2:0.07

3:0.05

4:0.07

5:0.10

6:0.07

7:0.08

8:0.10

9:0.07

10:0.07

11:0.10

Negative Logits

jured

-1.59

igham

-1.55

gger

-1.47

ihilation

-1.45

olicy

-1.44

achusetts

-1.42

 Oregon

-1.41

bid

-1.41

omas

-1.38

sburgh

-1.38

POSITIVE LOGITS

 indic

1.59

 confir

1.57

 praises

1.57

 rhythms

1.48

 gigs

1.42

 fingerprints

1.39

 specs

1.35

 dashboard

1.33

 accent

1.32

 accents

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.