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

1:0.07

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.09

8:0.09

9:0.06

10:0.08

11:0.09

Negative Logits

"))

-1.75

 SELECT

-1.55

 Asylum

-1.49

chard

-1.48

CRE

-1.48

rowth

-1.46

 crime

-1.45

 reserve

-1.43

sche

-1.43

Demand

-1.43

POSITIVE LOGITS

arta

1.79

omsky

1.76

 accomp

1.73

 biscuits

1.61

 Horus

1.60

 sidew

1.57

 towels

1.54

���

1.51

 diapers

1.50

reditary

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.