INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.07

1:0.07

2:0.08

3:0.06

4:0.09

5:0.08

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

Buff

-1.59

Param

-1.58

 gulf

-1.42

Instance

-1.41

 implication

-1.41

Correct

-1.39

estern

-1.39

ibal

-1.37

eger

-1.37

 Verse

-1.34

POSITIVE LOGITS

ufact

2.19

merce

1.65

ortment

1.53

umers

1.51

 obsess

1.48

tumblr

1.44

itiz

1.43

 answ

1.42

ngth

1.41

 rebate

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.