INDEX

Explanations

the word "on."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.08

2:0.10

3:0.08

4:0.09

5:0.09

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

license

-1.71

 Quote

-1.64

quickShipAvailable

-1.59

itations

-1.55

printed

-1.50

quished

-1.49

 tokens

-1.43

 Payments

-1.43

 Terms

-1.42

URL

-1.41

POSITIVE LOGITS

 Dame

1.82

town

1.67

 Latvia

1.63

abama

1.60

oots

1.53

hatt

1.50

eta

1.46

 partisan

1.46

hene

1.46

iets

1.45

Activations Density 0.000%

the word "on."

No Comments

No Known Activations