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

1:0.07

2:0.07

3:0.07

4:0.09

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

soDeliveryDate

-2.33

��

-1.96

��

-1.88

ahime

-1.74

 millennial

-1.71

 Millenn

-1.63

 Distribut

-1.62

 Parables

-1.62

chool

-1.61

 Cathy

-1.61

POSITIVE LOGITS

 finish

1.74

Reviewer

1.68

Benz

1.62

 flawless

1.58

izzard

1.54

:-

1.50

 handshake

1.49

formance

1.49

helm

1.49

rists

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.