INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.07

8:0.09

9:0.09

10:0.08

11:0.06

Negative Logits

().

-2.34

 sugg

-2.23

 largeDownload

-2.18

 optimizing

-2.06

um

-2.04

 indirectly

-2.03

vib

-2.01

 Firstly

-1.98

Firstly

-1.98

AAA

-1.97

POSITIVE LOGITS

rg

2.54

 Attribution

2.37

aug

2.32

osi

2.20

lesiastical

2.17

ldom

2.17

roma

2.16

tern

2.15

alions

2.15

clave

2.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.