INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.08

1:0.09

2:0.06

3:0.07

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.10

10:0.07

11:0.08

Negative Logits

 laughter

-2.74

 applause

-2.66

 ripple

-2.28

 Pulitzer

-2.17

 grin

-2.16

laughter

-2.06

 chuckle

-2.06

rican

-2.04

 peac

-2.04

 gigg

-1.96

POSITIVE LOGITS

 manually

2.19

essential

2.18

��

2.18

Firstly

2.16

 Sector

2.13

 Tycoon

2.12

龍�

1.95

imen

1.91

 Faction

1.91

�

1.87

Activations Density 0.000%

No Known Activations

This feature has no known activations.