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

0:0.08

1:0.06

2:0.09

3:0.08

4:0.09

5:0.07

6:0.09

7:0.07

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

roud

-1.76

erenn

-1.67

��

-1.56

ossier

-1.53

isible

-1.52

ENA

-1.52

DragonMagazine

-1.52

brance

-1.51

��

-1.51

Fn

-1.46

POSITIVE LOGITS

shock

1.72

 sucked

1.57

vs

1.48

wash

1.48

cause

1.43

jee

1.42

 tilted

1.38

Shy

1.34

 injections

1.33

uv

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.