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

0:0.07

1:0.05

2:0.09

3:0.07

4:0.10

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.10

11:0.08

Negative Logits

gans

-1.92

ollah

-1.81

nuclear

-1.78

ieri

-1.74

 sued

-1.65

 guarant

-1.63

 poultry

-1.58

 Rutherford

-1.55

 govern

-1.54

apons

-1.49

POSITIVE LOGITS

�

2.04

 largeDownload

1.89

Example

1.69

Diff

1.65

�

1.63

Icon

1.62

AU

1.60

Vert

1.57

 Somew

1.55

�

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.