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

3:0.09

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 Cosponsors

-2.13

 Americ

-2.00

nces

-1.99

 looph

-1.85

 ignor

-1.82

 disg

-1.75

Poc

-1.74

nown

-1.72

 Ajax

-1.69

 hypoc

-1.68

POSITIVE LOGITS

robe

1.67

 Workshop

1.67

Kate

1.65

lower

1.64

Dust

1.63

 shine

1.61

Rose

1.58

 Dove

1.57

UV

1.57

Laura

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.