INDEX

Explanations

phrases and terms associated with networks and connections

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.07

3:0.04

4:0.05

5:0.02

6:0.08

7:0.38

8:0.03

9:0.04

10:0.10

11:0.11

Negative Logits

jee

-1.74

*/(

-1.57

神

-1.53

terness

-1.51

 Overt

-1.36

joy

-1.33

 Simone

-1.33

etti

-1.31

azes

-1.29

inth

-1.29

POSITIVE LOGITS

 contacts

1.67

 networks

1.58

 communications

1.51

CDC

1.50

 network

1.47

Rog

1.41

 spies

1.39

 wireless

1.38

 telecom

1.35

 telecommunications

1.35

Activations Density 0.007%

phrases and terms associated with networks and connections

No Comments

No Known Activations