INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

5:0.08

6:0.08

7:0.07

8:0.09

9:0.09

10:0.07

11:0.07

Negative Logits

Mods

-1.41

Nap

-1.41

ゴン

-1.40

minster

-1.39

ritz

-1.36

Madison

-1.34

rants

-1.33

Ohio

-1.33

rises

-1.32

Home

-1.32

POSITIVE LOGITS

 Marketable

1.61

 advant

1.58

 describ

1.47

」

1.44

tein

1.40

ּ

1.36

 INCLUD

1.34

»

1.31

hap

1.31

?'

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.