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

1:0.06

2:0.09

3:0.09

4:0.06

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

Lake

-1.55

 Lake

-1.46

 Gulf

-1.44

lly

-1.42

 capital

-1.41

Bet

-1.40

hoe

-1.40

 veto

-1.38

 natives

-1.38

 Frequ

-1.37

POSITIVE LOGITS

ーク

1.75

◼

1.57

estern

1.55

ettes

1.53

enment

1.53

akeru

1.52

ourning

1.52

thood

1.52

escent

1.51

ngth

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.