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

0:0.03

1:0.02

2:0.13

3:0.15

4:0.09

5:0.05

6:0.05

7:0.12

8:0.05

9:0.05

10:0.14

11:0.08

Negative Logits

��極

-1.72

 demos

-1.52

Vs

-1.43

ibles

-1.41

 Curve

-1.40

 Factor

-1.39

 Physics

-1.38

ources

-1.38

 Cortex

-1.36

POSITIVE LOGITS

minist

1.74

 guiActive

1.73

ouver

1.64

STATE

1.60

lished

1.57

osher

1.54

 memorandum

1.54

EMBER

1.53

 impeachment

1.51

 hereby

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.