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

1:0.07

2:0.10

3:0.08

4:0.07

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

inventoryQuantity

-1.66

 understatement

-1.57

 Reincarn

-1.54

 hindsight

-1.49

 clamp

-1.44

flex

-1.43

 mortar

-1.43

 loosen

-1.42

 figur

-1.41

stretched

-1.40

POSITIVE LOGITS

encia

1.92

Interstitial

1.89

insula

1.70

arios

1.68

boarding

1.66

Pages

1.64

 Publishers

1.60

 Submission

1.60

 Distribution

1.59

ORTS

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.