INDEX

Explanations

references to specific geological and environmental events or entities

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

0:0.04

1:0.01

2:0.07

3:0.08

4:0.06

5:0.07

6:0.04

7:0.06

8:0.05

9:0.11

10:0.18

11:0.16

Negative Logits

Registered

-1.55

VICE

-1.52

 register

-1.45

�

-1.44

UD

-1.43

 self

-1.41

AW

-1.36

 Faces

-1.33

 Entered

-1.33

 SELECT

-1.32

POSITIVE LOGITS

 asteroid

2.01

milo

1.98

MpServer

1.88

htaking

1.86

mone

1.79

pox

1.78

haps

1.77

omorphic

1.75

 comet

1.75

 colonization

1.75

Activations Density 0.001%

references to specific geological and environmental events or entities

No Comments

No Known Activations