INDEX

Explanations

references to specific judicial circuits and districts

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

0:0.01

1:0.01

2:0.25

3:0.06

4:0.14

5:0.03

6:0.08

7:0.07

8:0.08

9:0.04

10:0.07

11:0.10

Negative Logits

 veins

-1.77

 pores

-1.57

eor

-1.54

 punches

-1.51

 wrinkles

-1.46

pect

-1.42

 arsen

-1.37

 jaws

-1.37

 bubbles

-1.37

 disg

-1.36

POSITIVE LOGITS

alion

1.63

mA

1.62

WARN

1.59

龍

1.51

iHUD

1.44

orum

1.37

iors

1.35

ANCE

1.34

FML

1.30

aid

1.30

Activations Density 0.001%

references to specific judicial circuits and districts

No Comments

No Known Activations