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

1:0.07

2:0.08

3:0.07

4:0.09

5:0.08

6:0.07

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 deleg

-1.88

 farmers

-1.78

 leadership

-1.69

 needy

-1.63

 charities

-1.62

 sustainability

-1.61

 compan

-1.61

reprene

-1.60

GAN

-1.57

 disadvantaged

-1.57

POSITIVE LOGITS

photos

2.00

Plex

1.75

ifix

1.75

 Reaction

1.75

 snapped

1.66

rontal

1.61

Images

1.57

OTOS

1.56

 Shroud

1.56

�

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.