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

4:0.09

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

Pa

-1.57

sung

-1.55

_-_

-1.50

 perpetrated

-1.48

 fond

-1.46

 Mane

-1.44

Against

-1.44

Bj

-1.42

jer

-1.37

Wisconsin

-1.37

POSITIVE LOGITS

artments

1.93

escape

1.78

sheets

1.74

sheet

1.57

tained

1.55

cius

1.54

outer

1.52

azine

1.51

elist

1.50

guide

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.