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

2:0.08

3:0.08

4:0.07

5:0.07

6:0.11

7:0.08

8:0.08

9:0.07

10:0.09

11:0.10

Negative Logits

Weiss

-1.80

 Fraser

-1.70

 Weiss

-1.65

█

-1.63

 Springs

-1.59

 McCabe

-1.59

 Foundation

-1.58

██

-1.55

RSA

-1.51

azo

-1.51

POSITIVE LOGITS

 dips

1.74

 Bought

1.71

ゴン

1.66

icides

1.64

ometimes

1.64

tracks

1.62

 roundup

1.60

eteenth

1.60

onom

1.58

 Overs

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.