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

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.06

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 Ratt

-1.78

�

-1.70

sts

-1.65

 Scar

-1.60

 Rober

-1.58

 Unlock

-1.58

ilater

-1.57

 Seeds

-1.57

 Thick

-1.56

 Weak

-1.53

POSITIVE LOGITS

afa

2.32

ashtra

1.98

holders

1.76

 differe

1.67

ween

1.65

holder

1.59

ghazi

1.57

clinton

1.56

nai

1.51

folk

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.