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

0:0.09

1:0.07

2:0.07

3:0.08

4:0.09

5:0.09

6:0.09

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

abases

-2.02

itars

-1.89

 ordinances

-1.84

oln

-1.75

 denominations

-1.72

 presses

-1.72

atives

-1.70

esters

-1.68

 searches

-1.66

 pumps

-1.66

POSITIVE LOGITS

 Situation

1.76

Thumbnail

1.73

 supra

1.69

tip

1.67

者

1.61

 sleeper

1.56

 sting

1.55

;;;;;;;;

1.52

 SECTION

1.49

ahn

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.