INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.08

1:0.06

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

'[

-1.45

 synth

-1.38

 tears

-1.36

 sensation

-1.36

 needles

-1.33

'?

-1.33

の�

-1.32

 apologised

-1.31

 rapt

-1.29

 transporter

-1.26

POSITIVE LOGITS

soType

2.05

BuyableInstoreAndOnline

1.84

 Skies

1.75

ahime

1.73

 Brill

1.73

clus

1.67

boa

1.65

 Builder

1.59

 ende

1.56

 Clash

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.