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

1:0.06

2:0.08

3:0.09

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

staff

-1.70

pel

-1.64

Reviewer

-1.60

tein

-1.51

atham

-1.51

ancial

-1.50

 skim

-1.48

 parsed

-1.46

-+

-1.43

cuts

-1.42

POSITIVE LOGITS

�

1.47

 alarms

1.43

Joy

1.39

FLAG

1.37

 congratulations

1.35

Jess

1.35

 Messiah

1.35

Issue

1.33

jog

1.32

MVP

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.