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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.08

4:0.07

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 Rudy

-2.02

 furious

-1.97

 Camera

-1.96

 riot

-1.92

 Casino

-1.90

 Metro

-1.88

 Rugby

-1.86

 Movie

-1.82

�

-1.80

 lifeless

-1.79

POSITIVE LOGITS

hower

2.55

psc

2.28

owship

2.20

=-=-=-=-

2.06

 guiIcon

2.04

soDeliveryDate

2.02

iaries

2.00

conservancy

2.00

 cures

1.99

®

1.97

Activations Density 0.000%

No Known Activations

This feature has no known activations.