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

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

 Sporting

-1.76

advertisement

-1.72

reason

-1.68

ages

-1.65

 saliva

-1.61

 Sting

-1.61

 Tears

-1.61

uckles

-1.61

 Mechdragon

-1.60

 Pavel

-1.59

POSITIVE LOGITS

Reviewer

2.18

agonist

1.84

udeau

1.82

externalActionCode

1.81

 autonomy

1.72

agonists

1.71

ipolar

1.65

 oppos

1.65

 cycl

1.62

 integration

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.