INDEX

Explanations

references to various social or cultural phenomena and their implications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.02

2:0.13

3:0.06

4:0.09

5:0.08

6:0.02

7:0.03

8:0.19

9:0.06

10:0.07

11:0.13

Negative Logits

tein

-1.66

heet

-1.55

onom

-1.47

apter

-1.47

ler

-1.45

heed

-1.40

emort

-1.37

tera

-1.37

athy

-1.36

farious

-1.35

POSITIVE LOGITS

soDeliveryDate

1.78

depending

1.66

runners

1.52

 enthusi

1.42

inline

1.40

Interstitial

1.39

ONES

1.34

 depending

1.33

 Schwarzenegger

1.32

 respectively

1.32

Activations Density 0.018%

references to various social or cultural phenomena and their implications

No Comments

No Known Activations