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

0:0.07

1:0.09

2:0.09

3:0.07

4:0.07

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

letters

-3.08

Strength

-2.68

warts

-2.59

wart

-2.58

colo

-2.58

ographs

-2.51

opath

-2.47

stal

-2.43

USB

-2.42

oldemort

-2.40

POSITIVE LOGITS

 Seas

3.06

 Volcano

2.78

 Chance

2.67

 Peninsula

2.55

 Takeru

2.50

uden

2.50

Kry

2.48

Zoo

2.44

Map

2.43

 Earthquake

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.