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

0:0.09

1:0.07

2:0.10

3:0.07

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 secondly

-1.94

 additionally

-1.58

 deepen

-1.54

also

-1.50

 introduce

-1.50

theless

-1.50

 refine

-1.49

 logos

-1.48

 divest

-1.47

 broaden

-1.47

POSITIVE LOGITS

untarily

1.89

cone

1.89

adelphia

1.83

answered

1.76

gal

1.68

alog

1.64

itor

1.63

ornia

1.61

duction

1.61

CHO

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.