INDEX

Explanations

phrases indicating funding sources or financial support

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

3:0.05

4:0.16

5:0.04

6:0.06

7:0.27

8:0.03

9:0.03

10:0.14

11:0.11

Negative Logits

ettings

-1.69

scape

-1.69

otiation

-1.66

chat

-1.65

perty

-1.64

jong

-1.61

ciation

-1.60

oland

-1.59

ignty

-1.58

ayn

-1.56

POSITIVE LOGITS

MpServer

1.77

govtrack

1.71

 supportive

1.51

 Jindal

1.47

 supporter

1.45

 philanthrop

1.42

 patronage

1.39

 Gund

1.39

 supporting

1.38

 funded

1.37

Activations Density 0.007%

phrases indicating funding sources or financial support

No Comments

No Known Activations