INDEX

Explanations

references to political concepts and discussions

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

1:0.02

2:0.06

3:0.07

4:0.12

5:0.03

6:0.03

7:0.35

8:0.05

9:0.03

10:0.07

11:0.08

Negative Logits

unker

-1.73

elected

-1.59

blers

-1.58

ヘ

-1.55

 runoff

-1.52

aline

-1.38

inos

-1.35

 saline

-1.31

uge

-1.29

igon

-1.28

POSITIVE LOGITS

 outlines

1.86

 plans

1.70

 outlining

1.69

 markings

1.57

 similarities

1.55

 correspondence

1.55

 wrinkles

1.53

Letter

1.52

 avenues

1.50

 initials

1.49

Activations Density 0.004%

references to political concepts and discussions

No Comments

No Known Activations