INDEX

Explanations

references to witnesses and testimony in legal or investigative 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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.03

2:0.07

3:0.04

4:0.02

5:0.09

6:0.15

7:0.27

8:0.07

9:0.02

10:0.07

11:0.10

Negative Logits

Quantity

-1.57

ゼウス

-1.46

inventoryQuantity

-1.35

 Manufact

-1.32

 Pricing

-1.29

�

-1.27

�

-1.26

Market

-1.23

 profitable

-1.23

 externalToEVAOnly

-1.20

POSITIVE LOGITS

 eyewitness

1.82

ewitness

1.72

 whom

1.53

emort

1.52

 witnesses

1.51

 testimonies

1.47

who

1.43

 corrobor

1.43

 narr

1.42

nsic

1.39

Activations Density 0.022%

references to witnesses and testimony in legal or investigative contexts

No Comments

No Known Activations