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

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

apter

-2.61

trace

-2.49

idis

-2.49

ecast

-2.37

owler

-2.16

arios

-2.14

llah

-2.14

 concess

-2.13

outheast

-2.10

ributed

-2.09

POSITIVE LOGITS

".[

2.13

!".

2.10

..............

2.06

}.

2.00

?).

1.98

".

1.97

[-

1.97

1.93

wow

1.90

神

1.90

Activations Density 0.000%

No Known Activations

This feature has no known activations.