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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

Tit

-1.61

 Irwin

-1.48

Tut

-1.47

 Amos

-1.44

 Romanian

-1.44

UGH

-1.43

ammy

-1.42

uggle

-1.40

vous

-1.38

igne

-1.38

POSITIVE LOGITS

Spoiler

1.56

mand

1.55

BIL

1.54

Enough

1.54

Vill

1.52

BU

1.48

grow

1.47

ailable

1.47

Plot

1.46

 monarchy

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.