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

2:0.09

3:0.09

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Interior

-1.77

 deterioration

-1.67

 intervals

-1.64

 recourse

-1.57

 seams

-1.57

 Superman

-1.55

 proponents

-1.55

 calves

-1.55

—

-1.53

 dstg

-1.53

POSITIVE LOGITS

vin

2.09

helle

2.05

pg

1.80

wn

1.76

 Volunte

1.73

 pione

1.73

ftime

1.73

cyclop

1.71

�

1.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.