INDEX

Explanations

themes of trust and skepticism in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.09

3:0.07

4:0.33

5:0.04

6:0.03

7:0.15

8:0.05

9:0.03

10:0.06

11:0.07

Negative Logits

emetery

-1.55

ilogy

-1.53

 wonder

-1.50

 rename

-1.38

 retro

-1.38

icter

-1.37

 prox

-1.37

 commemorate

-1.36

undown

-1.35

ornia

-1.34

POSITIVE LOGITS

SpaceEngineers

2.08

 Allaah

1.65

 Cosponsors

1.54

inventoryQuantity

1.46

 Flavoring

1.41

>[

1.40

ocrates

1.39

nor

1.37

ADVERTISEMENT

1.36

 instructors

1.36

Activations Density 0.006%

themes of trust and skepticism in various contexts

No Comments

No Known Activations