INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.14

2:0.08

3:0.09

4:0.06

5:0.08

6:0.06

7:0.06

8:0.08

9:0.08

10:0.08

11:0.06

Negative Logits

 aggrav

-1.77

 lanes

-1.57

 Gallup

-1.52

 Achilles

-1.45

okia

-1.45

awa

-1.44

 Recomm

-1.42

 assum

-1.42

adoes

-1.41

ukong

-1.41

POSITIVE LOGITS

tsy

1.80

WB

1.77

PG

1.72

ML

1.62

gmail

1.60

ARGET

1.60

Offline

1.60

venture

1.58

Wing

1.56

 unpublished

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.