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

0:0.06

1:0.10

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.06

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

etc

-1.91

 Born

-1.72

 newsp

-1.66

 Blanc

-1.54

ended

-1.49

etc

-1.48

 posture

-1.48

 dimensions

-1.47

Interstitial

-1.46

RT

-1.45

POSITIVE LOGITS

ombat

1.77

OOOO

1.73

aiden

1.71

umerable

1.66

opoly

1.65

owder

1.65

bably

1.65

loads

1.62

keyes

1.59

onut

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.