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

0:0.09

1:0.07

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.07

8:0.09

9:0.09

10:0.07

11:0.08

Negative Logits

illance

-1.76

support

-1.70

ansom

-1.68

athe

-1.66

 Nightmares

-1.61

nsics

-1.60

 Copyright

-1.59

 Neurolog

-1.57

protection

-1.56

cms

-1.53

POSITIVE LOGITS

 Word

1.80

ixel

1.72

ipl

1.71

 Hindi

1.68

 Miche

1.61

Gaw

1.61

 Designer

1.60

Word

1.59

 finer

1.58

 Gujar

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.