INDEX

Explanations

instances of the word "read" and related phrases indicating reading or waiting

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

1:0.02

2:0.07

3:0.08

4:0.10

5:0.03

6:0.38

7:0.04

8:0.05

9:0.04

10:0.06

11:0.04

Negative Logits

 redes

-1.53

clave

-1.36

pora

-1.27

 Lans

-1.21

 Cascade

-1.17

 Alpine

-1.11

 Providence

-1.10

rency

-1.10

 maritime

-1.10

 staging

-1.10

POSITIVE LOGITS

%%%%

1.47

ω

1.44

ESE

1.41

 dunno

1.39

etheless

1.35

�

1.32

laughs

1.32

!!!!

1.31

fw

1.29

LESS

1.26

Activations Density 0.050%

instances of the word "read" and related phrases indicating reading or waiting

No Comments

No Known Activations