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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.09

6:0.07

7:0.08

8:0.06

9:0.10

10:0.08

11:0.07

Negative Logits

 consequ

-1.61

 Hispan

-1.60

 academ

-1.59

«

-1.54

 Ukrain

-1.52

 deport

-1.47

 unaff

-1.44

 Niger

-1.44

 disrupted

-1.44

Yen

-1.41

POSITIVE LOGITS

erella

1.61

era

1.58

ARC

1.58

assis

1.58

ellar

1.55

ggles

1.53

lot

1.53

dragon

1.52

bris

1.52

Had

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.