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

3:0.07

4:0.08

5:0.07

6:0.07

7:0.08

8:0.09

9:0.07

10:0.09

11:0.10

Negative Logits

 Context

-1.66

 Boolean

-1.63

 Bagg

-1.58

 Oracle

-1.54

 Content

-1.52

 Wang

-1.51

 intervening

-1.51

XI

-1.50

 Storm

-1.50

CVE

-1.47

POSITIVE LOGITS

lder

2.01

gain

2.00

ovember

1.95

ortion

1.83

electric

1.79

ⓘ

1.76

inqu

1.73

jobs

1.71

 manif

1.68

boa

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.