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

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.06

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

Reviewed

-2.29

IUM

-1.96

reviewed

-1.94

eaturing

-1.90

ITS

-1.88

redients

-1.78

WHERE

-1.74

asive

-1.73

 subscribe

-1.73

orest

-1.73

POSITIVE LOGITS

 restraining

1.94

 Sting

1.89

 ejac

1.80

Nin

1.77

 Typhoon

1.67

 retaliation

1.57

 extingu

1.55

Mia

1.55

nam

1.55

 retali

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.