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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.10

2:0.07

3:0.05

4:0.09

5:0.10

6:0.08

7:0.09

8:0.07

9:0.08

10:0.07

11:0.09

Negative Logits

 morphine

-1.79

fav

-1.50

 chlorine

-1.48

brance

-1.42

 dams

-1.40

 Prev

-1.38

Pip

-1.36

 competition

-1.36

 serotonin

-1.35

 domination

-1.34

POSITIVE LOGITS

heast

1.95

oute

1.66

Untitled

1.59

eson

1.57

overe

1.57

 ACTIONS

1.53

Arch

1.51

ANCE

1.49

eton

1.49

ropolis

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.