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

1:0.06

2:0.09

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

thood

-2.01

ython

-1.99

isine

-1.80

AME

-1.79

TeX

-1.79

HTML

-1.77

anguages

-1.77

ciating

-1.70

eq

-1.67

EVs

-1.62

POSITIVE LOGITS

 fathers

1.61

 desp

1.52

 sweep

1.50

Kok

1.48

Lau

1.46

 divert

1.44

 setback

1.41

ris

1.40

 petition

1.39

 disp

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.