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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.09

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

 tails

-2.46

¥

-2.36

 Logged

-2.32

itch

-2.30

-2.25

 Irving

-2.23

 Hills

-2.20

-2.18

 nail

-2.16

soType

-2.13

POSITIVE LOGITS

TPPStreamerBot

2.75

��

2.68

odder

2.67

Compan

2.64

udeb

2.58

 learners

2.52

 healer

2.52

Pv

2.48

acters

2.43

 podcast

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.