INDEX

Explanations

phrases related to childhood and adolescent development

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

0:0.03

1:0.01

2:0.09

3:0.09

4:0.08

5:0.06

6:0.04

7:0.07

8:0.07

9:0.05

10:0.24

11:0.12

Negative Logits

Score

-1.59

zens

-1.53

votes

-1.53

 dissenting

-1.50

 parody

-1.49

 acron

-1.46

boro

-1.46

reply

-1.44

osponsors

-1.40

onyms

-1.39

POSITIVE LOGITS

 onwards

1.93

 onset

1.79

 onward

1.76

 transitions

1.73

 initiation

1.71

 exposures

1.60

 transition

1.58

 progressed

1.57

 phases

1.56

 thereafter

1.53

Activations Density 0.006%

phrases related to childhood and adolescent development

No Comments

No Known Activations