INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.05

2:0.10

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.06

Negative Logits

azo

-1.81

ois

-1.65

 retarded

-1.65

exempt

-1.59

adas

-1.57

ntax

-1.53

 inhibited

-1.47

ensis

-1.45

otin

-1.45

eff

-1.43

POSITIVE LOGITS

 Ultr

1.61

Hok

1.59

 Savannah

1.51

 Crescent

1.50

 Sutherland

1.49

 Olympus

1.47

 Valkyrie

1.45

 Minneapolis

1.41

 Nare

1.39

 Thunderbolt

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.