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

0:0.09

1:0.08

2:0.07

3:0.09

4:0.09

5:0.06

6:0.09

7:0.08

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

�

-1.61

к

-1.53

 trou

-1.51

iage

-1.49

 lineage

-1.47

 Takeru

-1.40

 Collabor

-1.38

iona

-1.37

 Afric

-1.36

||||

-1.35

POSITIVE LOGITS

soDeliveryDate

1.74

thumbnails

1.53

priv

1.45

elected

1.45

asking

1.44

ecause

1.43

vernment

1.41

warts

1.41

limits

1.41

tube

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.