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

0:0.09

1:0.06

2:0.09

3:0.09

4:0.07

5:0.08

6:0.07

7:0.09

8:0.09

9:0.07

10:0.09

11:0.08

Negative Logits

 effortlessly

-1.70

utics

-1.67

ensional

-1.65

 sophistication

-1.64

ioxid

-1.63

surprisingly

-1.62

utterstock

-1.62

thens

-1.60

rir

-1.56

amer

-1.53

POSITIVE LOGITS

1.74

FAA

1.50

.''

1.43

 McGu

1.42

 Ellison

1.38

 Robinson

1.38

 quota

1.37

 Acquisition

1.37

 Installation

1.35

 advis

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.