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

0:0.06

1:0.05

2:0.12

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.07

10:0.07

11:0.07

Negative Logits

版

-1.61

 Bridges

-1.53

IUM

-1.49

��

-1.48

 Trials

-1.46

rossover

-1.45

�

-1.43

Lear

-1.42

Learning

-1.42

 Notre

-1.42

POSITIVE LOGITS

plet

1.59

urance

1.56

eger

1.56

 Nicarag

1.55

pret

1.54

protected

1.51

emer

1.50

 squeeze

1.49

cale

1.49

competitive

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.