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

1:0.08

2:0.08

3:0.09

4:0.07

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.10

11:0.08

Negative Logits

 "$:/

-1.64

itely

-1.60

cribed

-1.52

-1.49

annon

-1.47

notations

-1.47

thumbnails

-1.46

ancies

-1.46

wra

-1.43

 ILCS

-1.42

POSITIVE LOGITS

 neigh

1.64

 Galile

1.63

 wiser

1.56

ASHINGTON

1.51

Jam

1.50

 Breed

1.48

 ammonia

1.37

 valves

1.36

 worsening

1.36

 Cascade

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.