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

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 rife

-2.04

 lawy

-2.03

 akin

-2.00

 riddled

-1.92

 begging

-1.86

 Azerb

-1.82

 defiant

-1.80

 upholding

-1.78

 policeman

-1.72

 fraught

-1.71

POSITIVE LOGITS

isk

1.94

obook

1.78

Meg

1.70

 Jelly

1.66

otte

1.64

omer

1.63

amba

1.61

ftime

1.60

quart

1.58

Rx

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.