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

2:0.07

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.07

Negative Logits

 respons

-1.89

 shape

-1.77

 gears

-1.74

 mathematics

-1.74

 shapes

-1.70

 geometry

-1.69

 oscill

-1.68

 overturn

-1.62

 demol

-1.61

 calculus

-1.59

POSITIVE LOGITS

ufact

2.41

isSpecialOrderable

2.04

vation

1.92

itably

1.89

 Intake

1.80

ogh

1.80

mitting

1.75

ONSORED

1.74

*:

1.73

beit

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.