INDEX

Explanations

expressions of strong positive sentiment or affection

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

0:0.03

1:0.02

2:0.16

3:0.06

4:0.12

5:0.03

6:0.05

7:0.27

8:0.06

9:0.04

10:0.05

11:0.06

Negative Logits

 puberty

-1.57

orders

-1.56

ivist

-1.51

 crises

-1.49

 crisis

-1.45

iries

-1.42

rollment

-1.41

igate

-1.40

 debts

-1.39

rop

-1.38

POSITIVE LOGITS

��

1.74

�

1.59

laughs

1.48

%%%%

1.46

blogspot

1.45

hend

1.44

 Somew

1.44

 aest

1.43

★★

1.40

 sacrific

1.38

Activations Density 0.007%

expressions of strong positive sentiment or affection

No Comments

No Known Activations