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

1:0.06

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

adies

-1.70

 compromises

-1.60

 protests

-1.56

Film

-1.49

 eSports

-1.46

00200000

-1.45

ESPN

-1.42

 leaked

-1.41

enty

-1.41

archives

-1.40

POSITIVE LOGITS

 experien

1.90

ahime

1.84

bered

1.80

 Siber

1.79

lished

1.78

�

1.76

 answ

1.75

️

1.69

bis

1.58

gart

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.