INDEX

Explanations

references to specific cases or events and their occurrences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

0:0.02

1:0.02

2:0.14

3:0.18

4:0.06

5:0.04

6:0.13

7:0.04

8:0.06

9:0.07

10:0.08

11:0.12

Negative Logits

 endif

-1.58

ModLoader

-1.54

=-=-=-=-

-1.52

========

-1.48

 insepar

-1.45

 evolves

-1.44

û

-1.39

////////////////////////////////

-1.37

 fulf

-1.36

iferation

-1.35

POSITIVE LOGITS

���

1.62

IPS

1.46

 Samsung

1.40

oard

1.38

amba

1.32

cases

1.31

uckland

1.31

 Starbucks

1.30

 Gupta

1.29

 Blumenthal

1.27

Activations Density 0.004%

references to specific cases or events and their occurrences

No Comments

No Known Activations