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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.09

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

opian

-1.78

election

-1.68

 bipartisan

-1.60

erie

-1.56

 acquaintance

-1.56

udeb

-1.53

alysed

-1.53

illy

-1.53

auri

-1.53

arie

-1.52

POSITIVE LOGITS

flows

2.02

gul

1.86

 Pigs

1.81

 spons

1.73

 pant

1.66

Vet

1.66

paces

1.62

Kut

1.61

ategory

1.59

 Lump

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.