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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.10

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.06

10:0.08

11:0.07

Negative Logits

Pik

-2.60

 earthquake

-2.56

 tsun

-2.53

catentry

-2.42

 avalanche

-2.38

 iceberg

-2.33

 quake

-2.32

angelo

-2.31

 Avatar

-2.29

 Covenant

-2.28

POSITIVE LOGITS

Metro

3.16

MET

3.06

NRS

2.90

TTC

2.86

Mor

2.86

dyl

2.75

>>

2.72

itars

2.68

OY

2.65

Fuck

2.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.