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

Head Attr Weights

0:0.07

1:0.06

2:0.09

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.06

10:0.07

11:0.10

Negative Logits

Downloadha

-1.71

 amput

-1.64

 throats

-1.58

�

-1.58

�

-1.57

�

-1.54

java

-1.51

 tyranny

-1.49

 Kansas

-1.45

 Spart

-1.43

POSITIVE LOGITS

ividual

2.03

etsy

1.76

ril

1.71

ulk

1.62

vertisement

1.62

ucci

1.61

post

1.60

 Costume

1.60

rame

1.57

ete

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.