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

0:0.08

1:0.08

2:0.09

3:0.06

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 sponge

-2.98

 Sponge

-2.72

 Spoon

-2.66

 astronaut

-2.57

Sai

-2.56

Dow

-2.52

 Brune

-2.45

 Columbia

-2.40

 Stones

-2.39

�

-2.39

POSITIVE LOGITS

reon

3.12

Els

3.05

soDeliveryDate

2.88

habi

2.86

yip

2.85

vez

2.75

rez

2.70

Revolution

2.57

enfranch

2.57

 fuzz

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.