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

1:0.06

2:0.08

3:0.10

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

き

-1.67

ILA

-1.63

bol

-1.57

 ducks

-1.56

方

-1.54

angular

-1.54

エル

-1.53

 wraps

-1.51

�

-1.51

Trivia

-1.51

POSITIVE LOGITS

elled

1.72

rael

1.58

 adequately

1.55

cale

1.52

liam

1.51

ensus

1.50

urgical

1.49

 traged

1.49

oppers

1.49

��

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.