INDEX

Explanations

No Explanations Found

New Auto-Interp

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

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 subscriber

-1.69

 deduction

-1.60

 playbook

-1.59

 Narr

-1.58

 incentive

-1.57

 account

-1.56

 rece

-1.55

 mileage

-1.54

 deduct

-1.52

 viewing

-1.50

POSITIVE LOGITS

cussion

1.81

uten

1.75

leness

1.75

エ

1.74

iour

1.69

-+-+

1.63

utan

1.61

版

1.60

uni

1.58

roma

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.