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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.09

8:0.09

9:0.08

10:0.06

11:0.08

Negative Logits

��

-2.56

????????

-2.56

SPONSORED

-2.43

HAEL

-2.22

pecially

-2.14

????

-2.11

Senior

-2.09

catentry

-2.08

allic

-2.06

abe

-2.02

POSITIVE LOGITS

ggles

2.44

 squats

2.27

 commute

2.15

 congestion

2.14

 tweaks

2.12

 climbs

2.04

uador

1.99

pee

1.99

orbit

1.97

 Buffer

1.94

Activations Density 0.000%

No Known Activations

This feature has no known activations.