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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

contin

-2.02

wire

-1.99

regulated

-1.97

uploads

-1.94

isol

-1.88

iland

-1.84

illus

-1.82

demand

-1.79

verified

-1.79

ILY

-1.77

POSITIVE LOGITS

 Chrysler

1.69

 Chinatown

1.64

 Eastern

1.63

 Jericho

1.58

 Johnny

1.58

 Hispan

1.57

 Silver

1.55

 Dracula

1.54

 tallest

1.52

 Wheat

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.