INDEX

Explanations

phrases that indicate actions or states of being involving the word "by."

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

0:0.03

1:0.02

2:0.22

3:0.06

4:0.12

5:0.03

6:0.06

7:0.17

8:0.06

9:0.04

10:0.06

11:0.09

Negative Logits

 waterways

-1.63

 Philly

-1.62

SEA

-1.57

VA

-1.55

ヴ

-1.55

-1.51

 pulp

-1.46

�

-1.46

ADVERTISEMENT

-1.46

Philadelphia

-1.45

POSITIVE LOGITS

enhagen

2.11

cius

1.98

agonist

1.87

rious

1.80

amiliar

1.78

 Cosponsors

1.66

bryce

1.63

lyak

1.61

avid

1.61

 Baron

1.60

Activations Density 0.000%

phrases that indicate actions or states of being involving the word "by."

No Comments

No Known Activations