INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.07

3:0.08

4:0.07

5:0.09

6:0.09

7:0.09

8:0.07

9:0.07

10:0.07

11:0.09

Negative Logits

 liabilities

-1.47

 inherited

-1.41

 factors

-1.37

 pathogens

-1.35

 comparisons

-1.35

 acquisitions

-1.35

 classification

-1.35

 matchup

-1.32

 factor

-1.29

 holdings

-1.29

POSITIVE LOGITS

�

1.53

JR

1.52

jc

1.48

OUP

1.48

装

1.47

��

1.44

�

1.44

ーティ

1.43

��

1.43

EStreamFrame

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.