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

1:0.07

2:0.09

3:0.09

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

ileaks

-1.89

ebin

-1.76

appropriately

-1.76

 Mehran

-1.72

 candid

-1.72

esty

-1.72

agraph

-1.70

 leaks

-1.70

adata

-1.68

yrinth

-1.66

POSITIVE LOGITS

 Moral

2.00

mA

1.96

 Nobel

1.89

 Barbarian

1.73

thood

1.72

swing

1.69

Primary

1.68

 tolerance

1.65

 Fundamental

1.64

 barb

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.