INDEX

Explanations

the article "a"

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

0:0.09

1:0.04

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 disclosed

-1.89

essler

-1.87

heter

-1.73

owder

-1.70

etimes

-1.70

tip

-1.60

idium

-1.59

ierce

-1.59

enna

-1.59

uron

-1.59

POSITIVE LOGITS

ンジ

1.66

 reperto

1.64

BAS

1.59

エル

1.55

\\\\\\\\

1.54

 imitation

1.53

 Rodrig

1.46

 cooperative

1.45

 Wonderland

1.45

 Rout

1.44

Activations Density 0.000%

the article "a"

No Comments

No Known Activations