INDEX

Explanations

pronouns and determiners used to reference entities

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

0:0.03

1:0.03

2:0.07

3:0.08

4:0.19

5:0.03

6:0.13

7:0.15

8:0.04

9:0.03

10:0.08

11:0.07

Negative Logits

ゴン

-1.65

 understatement

-1.51

javascript

-1.49

 persuasion

-1.46

rency

-1.46

 equivalents

-1.45

 anyways

-1.43

PLIED

-1.43

 consolation

-1.41

iology

-1.39

POSITIVE LOGITS

 cone

1.57

 perimeter

1.50

 cones

1.45

 broom

1.36

 objects

1.35

 waist

1.34

omever

1.33

 statue

1.32

 bolts

1.32

 formations

1.30

Activations Density 0.001%

pronouns and determiners used to reference entities

No Comments

No Known Activations