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

1:0.09

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

ilo

-1.97

glers

-1.96

agascar

-1.75

ilee

-1.67

opolis

-1.62

 tradem

-1.59

oga

-1.53

aiden

-1.52

 Firstly

-1.51

"]=>

-1.50

POSITIVE LOGITS

 solvent

1.63

HL

1.62

 levers

1.58

 untreated

1.55

 sequencing

1.52

 cushion

1.51

��

1.47

 mitochond

1.46

 rigged

1.44

Fib

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.