INDEX

Explanations

articles and determiners

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

2:0.15

3:0.05

4:0.08

5:0.04

6:0.16

7:0.17

8:0.03

9:0.04

10:0.08

11:0.11

Negative Logits

 Finder

-1.60

Stars

-1.48

-1.46

ukemia

-1.38

Saharan

-1.38

stars

-1.35

 Inside

-1.35

ispers

-1.33

ancies

-1.32

ategories

-1.30

POSITIVE LOGITS

 miscon

1.72

 deterrent

1.64

 pinch

1.61

 excuse

1.61

 souven

1.61

 wrench

1.58

 watering

1.57

 precaution

1.56

 convenient

1.56

 salv

1.56

Activations Density 0.004%

articles and determiners

No Comments

No Known Activations