INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.07

2:0.07

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

illac

-3.14

 McAuliffe

-2.97

CA

-2.92

 Whitney

-2.86

displayText

-2.78

YC

-2.75

MIT

-2.73

 Cadillac

-2.71

HOU

-2.66

BLM

-2.64

POSITIVE LOGITS

 islands

2.90

 explan

2.69

 lords

2.59

 soils

2.55

 relie

2.53

 sponge

2.48

 volleyball

2.44

 drawer

2.42

 formations

2.40

sen

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.