INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.07

2:0.07

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

 Barnett

-2.82

eus

-2.76

taboola

-2.75

hua

-2.69

tti

-2.68

Blocks

-2.63

blocks

-2.56

 Quentin

-2.54

hl

-2.48

larg

-2.46

POSITIVE LOGITS

romy

2.91

 welf

2.72

 dementia

2.58

Nut

2.53

WARE

2.52

 sane

2.51

 insanity

2.49

 Cyborg

2.48

 amput

2.46

Sov

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.