INDEX

Explanations

terms related to archaeology, archaeological sites, and excavations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

mentions of archaeological digs and discoveries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.05

1:0.08

2:0.15

3:0.06

4:0.07

5:0.08

6:0.05

7:0.05

8:0.08

9:0.15

10:0.09

11:0.04

Negative Logits

EStreamFrame

-1.44

 blocker

-1.41

drawn

-1.31

 whining

-1.30

agame

-1.26

hearted

-1.26

puff

-1.25

esson

-1.25

otine

-1.24

 blockers

-1.21

POSITIVE LOGITS

 archae

2.25

 archaeologists

2.13

 Archae

2.05

 excav

1.83

 archaeological

1.79

gypt

1.79

 UNESCO

1.71

 excavation

1.69

 arche

1.67

 graves

1.61

Activations Density 0.027%

terms related to archaeology, archaeological sites, and excavations

mentions of archaeological digs and discoveries

No Comments

No Known Activations