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

0:0.08

1:0.05

2:0.09

3:0.08

4:0.09

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 misunder

-1.85

WithNo

-1.75

paio

-1.70

 enthusi

-1.65

 clich

-1.64

 Alban

-1.62

ONES

-1.62

 nodd

-1.62

ITS

-1.57

 seasoned

-1.55

POSITIVE LOGITS

 radius

1.85

ptoms

1.83

vert

1.68

idal

1.63

anos

1.63

 respectively

1.61

 trailing

1.57

feeding

1.57

astern

1.56

AppData

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.