INDEX

Explanations

references to locations and contextual settings in the narrative

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

2:0.09

3:0.06

4:0.18

5:0.02

6:0.21

7:0.16

8:0.03

9:0.03

10:0.05

11:0.07

Negative Logits

 Egyptians

-1.55

 Maxim

-1.50

 Poles

-1.42

 ingenuity

-1.34

isa

-1.32

 wielded

-1.32

 Dems

-1.31

 incumb

-1.24

 predecessors

-1.23

 Greeks

-1.23

POSITIVE LOGITS

 Situation

1.67

shape

1.61

 thro

1.52

 hurry

1.51

QB

1.48

 vicinity

1.43

 woods

1.43

▬▬

1.40

 limbo

1.39

 dumps

1.37

Activations Density 0.056%

references to locations and contextual settings in the narrative

No Comments

No Known Activations