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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Corpus

-1.70

 Luxem

-1.62

IUM

-1.59

 Intern

-1.54

GER

-1.53

edIn

-1.51

 Athlet

-1.51

 Herb

-1.50

 Rodham

-1.50

Wyr

-1.50

POSITIVE LOGITS

uci

1.93

 pressures

1.80

intendent

1.70

inventoryQuantity

1.68

 inhibitor

1.62

KT

1.61

cing

1.58

 inhib

1.56

hap

1.51

vantage

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.