INDEX

Explanations

references to interviews and discussions in various contexts

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.39

1:0.05

2:0.01

3:0.14

4:0.10

5:0.04

6:0.03

7:0.03

8:0.07

9:0.05

10:0.02

11:0.01

Negative Logits

reading

-1.57

Copy

-1.53

ウス

-1.50

Interstitial

-1.50

Driver

-1.48

Better

-1.46

urations

-1.38

universal

-1.38

sense

-1.38

ptions

-1.37

POSITIVE LOGITS

 alliance

1.68

 aisle

1.65

 area

1.64

 subdivision

1.56

 plaza

1.55

 frequ

1.53

 includ

1.52

 venue

1.52

 session

1.51

 forum

1.51

Activations Density 0.013%

references to interviews and discussions in various contexts

No Comments

No Known Activations