INDEX

Explanations

terms related to law enforcement and federal agencies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.08

3:0.05

4:0.05

5:0.03

6:0.36

7:0.04

8:0.03

9:0.04

10:0.13

11:0.10

Negative Logits

 Takeru

-1.20

ergy

-1.19

animate

-1.15

 Pradesh

-1.13

mson

-1.12

pole

-1.10

yip

-1.08

 increments

-1.08

 orbs

-1.07

 faire

-1.07

POSITIVE LOGITS

 Audit

1.44

ワン

1.20

Orn

1.13

 Editors

1.12

RG

1.11

arthed

1.11

speak

1.11

NSA

1.10

gerald

1.10

NI

1.09

Activations Density 0.019%

terms related to law enforcement and federal agencies

No Comments

No Known Activations