INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

1:0.06

2:0.08

3:0.08

4:0.09

5:0.09

6:0.08

7:0.08

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

pload

-1.75

��

-1.73

iencies

-1.71

geries

-1.69

apolis

-1.66

¶

-1.64

ivable

-1.57

Yug

-1.56

Neb

-1.56

ensable

-1.56

POSITIVE LOGITS

 spokesperson

1.71

ouf

1.68

heim

1.67

 spokesman

1.64

sam

1.60

mother

1.58

icist

1.56

 personality

1.50

heimer

1.50

ALSE

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.