INDEX

Explanations

instances of legal and political discussions surrounding regulations and actions taken by government entities

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

0:0.08

1:0.21

2:0.05

3:0.06

4:0.04

5:0.02

6:0.10

7:0.06

8:0.04

9:0.04

10:0.20

11:0.06

Negative Logits

cock

-3.12

OV

-2.98

hot

-2.92

alty

-2.75

Lat

-2.74

hol

-2.69

HUD

-2.67

roxy

-2.66

served

-2.64

NET

-2.62

POSITIVE LOGITS

Bec

7.15

Bec

5.27

bec

4.93

bec

4.11

Dek

3.54

Bis

3.28

 Bers

3.18

 Purs

3.15

 Decl

3.09

 Briggs

2.98

Activations Density 0.002%

instances of legal and political discussions surrounding regulations and actions taken by government entities

No Comments

No Known Activations