INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

tics

-2.86

anwhile

-2.83

rawdownloadcloneembedreportprint

-2.77

UTE

-2.68

states

-2.65

INE

-2.62

{"

-2.60

 hinges

-2.59

turned

-2.59

 Kingdoms

-2.58

POSITIVE LOGITS

Interstitial

2.94

Gur

2.92

 Monetary

2.67

entle

2.60

 Miko

2.60

FM

2.56

 Muss

2.48

☆

2.47

 tremend

2.46

 stimulus

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.