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

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.09

9:0.07

10:0.07

11:0.09

Negative Logits

HRC

-1.76

 Declaration

-1.65

 Proud

-1.64

 speeches

-1.61

Pep

-1.60

 remarks

-1.58

 Hearing

-1.58

 Records

-1.58

 Speech

-1.58

roud

-1.56

POSITIVE LOGITS

 helicop

1.94

thora

1.82

Bat

1.77

icide

1.63

zona

1.62

ascade

1.62

thinkable

1.61

$$$$

1.59

 kidnap

1.55

seeking

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.