INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

ereo

-2.86

ernels

-2.72

advertising

-2.49

later

-2.46

 Waves

-2.46

History

-2.46

NFL

-2.46

 biome

-2.45

hiba

-2.43

 Roads

-2.41

POSITIVE LOGITS

psc

3.16

 Quit

3.11

 Quart

2.97

 Chap

2.75

ucket

2.74

TP

2.72

>>>>>>>>

2.62

puff

2.59

entin

2.53

Hua

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.