INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.14

2:0.05

3:0.09

4:0.04

5:0.07

6:0.09

7:0.06

8:0.09

9:0.09

10:0.11

11:0.04

Negative Logits

 relayed

-1.61

nis

-1.57

nikov

-1.56

iot

-1.54

oğ

-1.54

 antagon

-1.51

 doct

-1.49

 inhibited

-1.49

 nonetheless

-1.48

 withheld

-1.46

POSITIVE LOGITS

ahime

1.96

 Dwell

1.63

 Masquerade

1.60

 Maze

1.55

Heart

1.54

soType

1.53

��極

1.49

龍喚士

1.49

Single

1.48

 Warehouse

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.