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

1:0.08

2:0.09

3:0.08

4:0.08

5:0.06

6:0.08

7:0.08

8:0.10

9:0.08

10:0.07

11:0.08

Negative Logits

chenko

-2.06

 Shaw

-2.02

ucl

-1.94

 Pavel

-1.87

 Schwarzenegger

-1.81

 Cullen

-1.80

 Bale

-1.79

Kov

-1.76

Wed

-1.75

 Vaughan

-1.71

POSITIVE LOGITS

 independ

1.95

lords

1.79

 cryst

1.75

luck

1.70

Honest

1.65

覚醒

1.60

accompan

1.58

 plateau

1.56

 summit

1.51

shake

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.