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

0:0.07

1:0.06

2:0.09

3:0.08

4:0.09

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

 exhaustion

-1.79

 degradation

-1.49

 pouring

-1.48

 sniff

-1.48

ded

-1.46

 brut

-1.43

 beams

-1.42

 concluding

-1.42

 consensus

-1.39

quo

-1.39

POSITIVE LOGITS

MpServer

1.96

 Origins

1.93

actionDate

1.88

imester

1.85

cffffcc

1.79

��

1.77

 サーティワン

1.69

��

1.67

 Surgery

1.65

 Graveyard

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.