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

1:0.11

2:0.07

3:0.08

4:0.07

5:0.07

6:0.08

7:0.09

8:0.07

9:0.06

10:0.08

11:0.09

Negative Logits

 Scarborough

-1.60

 Shanahan

-1.50

 Sheldon

-1.50

 Sche

-1.50

 ESPN

-1.48

Sports

-1.45

dom

-1.44

 surrogate

-1.43

 Spur

-1.42

Cox

-1.41

POSITIVE LOGITS

ivas

1.98

rin

1.97

phrine

1.84

uran

1.81

imeo

1.80

ionic

1.74

imil

1.73

sembly

1.73

yip

1.73

jug

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.