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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.11

8:0.07

9:0.07

10:0.07

11:0.07

Negative Logits

 Mount

-1.72

 Bram

-1.54

 Capitol

-1.50

 Dead

-1.50

 Deadly

-1.49

 Greater

-1.48

 Auditor

-1.45

 Sleeping

-1.44

 underworld

-1.43

 Chamber

-1.43

POSITIVE LOGITS

viously

2.01

phi

1.99

sole

1.94

illus

1.87

ggles

1.82

wash

1.82

inian

1.80

orf

1.80

monkey

1.79

reat

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.