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

0:0.07

1:0.07

2:0.09

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Reviewer

-1.96

blers

-1.87

iasis

-1.87

selves

-1.80

irl

-1.73

ammers

-1.57

fighters

-1.56

especially

-1.54

users

-1.54

bsite

-1.53

POSITIVE LOGITS

 inaug

1.85

 revolutions

1.81

buquerque

1.70

itialized

1.51

 suprem

1.51

 emanc

1.51

 semin

1.50

 millenn

1.49

 cooperative

1.47

hattan

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.