INDEX

Explanations

actions related to transportation and movement of people or items

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.05

3:0.06

4:0.10

5:0.02

6:0.04

7:0.40

8:0.03

9:0.03

10:0.11

11:0.08

Negative Logits

 contributor

-1.54

 fuss

-1.52

 susceptibility

-1.40

etheless

-1.38

 reviewer

-1.38

 trend

-1.36

ulty

-1.35

 rivalry

-1.34

 bias

-1.34

ior

-1.34

POSITIVE LOGITS

 buses

1.65

ascus

1.58

acas

1.54

ijuana

1.54

 carts

1.54

 taxis

1.53

anwhile

1.48

rollers

1.47

 freight

1.44

 Passage

1.44

Activations Density 0.012%

actions related to transportation and movement of people or items

No Comments

No Known Activations