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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

utonium

-1.96

ustain

-1.81

exclusive

-1.73

-1.72

 regulates

-1.68

EGA

-1.67

 conserve

-1.66

sbm

-1.64

eco

-1.61

iband

-1.61

POSITIVE LOGITS

 screenshot

1.94

open

1.56

 preceding

1.55

 mound

1.55

 magnification

1.54

 embed

1.52

 table

1.51

 caption

1.50

 textual

1.48

 styl

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.