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

4:0.09

5:0.06

6:0.07

7:0.11

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

 gobl

-1.96

≡

-1.93

��

-1.80

}}

-1.77

 eleph

-1.72

 Prelude

-1.68

 protector

-1.66

 goat

-1.64

yip

-1.63

 amen

-1.62

POSITIVE LOGITS

IGN

2.09

Import

2.06

Commerce

1.94

URE

1.90

IONS

1.88

URES

1.85

IRE

1.81

ORY

1.76

Forge

1.75

Reviewer

1.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.