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

0:0.08

1:0.11

2:0.07

3:0.07

4:0.08

5:0.07

6:0.08

7:0.09

8:0.09

9:0.05

10:0.08

11:0.07

Negative Logits

 experien

-2.20

yip

-2.09

 accur

-2.01

cise

-1.97

ancies

-1.94

icular

-1.87

ionic

-1.85

cients

-1.82

ractor

-1.78

gart

-1.77

POSITIVE LOGITS

 Legion

1.61

public

1.60

 PUBLIC

1.57

Documents

1.57

 perjury

1.55

 SHARES

1.55

Recommend

1.53

SHARE

1.52

 Romeo

1.51

く

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.