INDEX

Explanations

instances of approval and authorization related to legislation or regulation

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

New Auto-Interp

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

1:0.02

2:0.06

3:0.04

4:0.22

5:0.05

6:0.02

7:0.31

8:0.03

9:0.03

10:0.07

11:0.07

Negative Logits

igi

-1.62

visible

-1.46

encers

-1.46

crow

-1.43

warts

-1.41

icken

-1.41

ulnerable

-1.39

luent

-1.38

bery

-1.37

lege

-1.37

POSITIVE LOGITS

 continuation

1.58

 proposal

1.54

 topp

1.54

 bids

1.53

bid

1.47

 shipment

1.39

 shipments

1.37

 proposals

1.34

 annexation

1.32

 bidding

1.32

Activations Density 0.008%

instances of approval and authorization related to legislation or regulation

No Comments

No Known Activations