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

0:0.08

1:0.05

2:0.10

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

arbon

-1.96

 arsen

-1.95

quartered

-1.95

obyl

-1.92

hran

-1.88

Fram

-1.83

oak

-1.81

urses

-1.79

ecause

-1.79

estones

-1.71

POSITIVE LOGITS

 rating

1.69

 rider

1.66

 visa

1.60

 deductions

1.59

 deduction

1.58

 Sanders

1.56

 FISA

1.56

TPP

1.56

 pardon

1.52

 opportunity

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.