INDEX

Explanations

references to actors and their roles in productions

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_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

0:0.03

1:0.03

2:0.07

3:0.08

4:0.08

5:0.06

6:0.04

7:0.05

8:0.04

9:0.08

10:0.30

11:0.08

Negative Logits

 Networks

-1.69

 Consumers

-1.66

weet

-1.65

acas

-1.64

SOURCE

-1.64

 Kraft

-1.64

lehem

-1.57

fuel

-1.55

itement

-1.55

sent

-1.54

POSITIVE LOGITS

 hinges

1.55

vet

1.53

 Fellowship

1.52

 hinge

1.51

 Angle

1.47

 healer

1.46

 placeholder

1.46

 unarmed

1.44

 entails

1.44

 shave

1.41

Activations Density 0.003%

references to actors and their roles in productions

No Comments

No Known Activations