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

0:0.11

1:0.05

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

CTV

-1.71

uve

-1.71

Mask

-1.55

voice

-1.53

Pause

-1.50

 berth

-1.49

Scope

-1.46

Else

-1.43

socket

-1.42

Scale

-1.42

POSITIVE LOGITS

artifacts

1.91

 assorted

1.65

DUI

1.54

cohol

1.51

ernels

1.49

oshenko

1.48

uggest

1.45

��

1.43

ugs

1.42

 sprinkled

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.