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

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 capabilities

-1.53

 capability

-1.50

 dich

-1.47

 branch

-1.42

 insign

-1.41

 prevalence

-1.39

 sustain

-1.39

comb

-1.38

 pers

-1.38

 advantages

-1.38

POSITIVE LOGITS

HAEL

1.99

abo

1.78

═

1.69

 Thib

1.65

 Rahul

1.55

 Canaver

1.55

 largeDownload

1.53

_-

1.53

 Moreno

1.50

 Saunders

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.