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

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.10

8:0.07

9:0.08

10:0.09

11:0.06

Negative Logits

 lineback

-1.77

ainers

-1.59

 Saud

-1.58

 Ashes

-1.53

apons

-1.51

parts

-1.50

 Harbaugh

-1.50

ukes

-1.46

iru

-1.45

olen

-1.44

POSITIVE LOGITS

者

1.73

 expire

1.48

Gi

1.44

Tesla

1.41

rc

1.40

 Surve

1.40

Release

1.38

 prelim

1.38

 Topic

1.37

DK

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.