INDEX

Explanations

terms related to various types of "un" prefixes or organizations

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

1:0.04

2:0.10

3:0.09

4:0.01

5:0.03

6:0.16

7:0.11

8:0.07

9:0.06

10:0.09

11:0.15

Negative Logits

essen

-1.18

opoulos

-1.14

pecially

-1.03

veland

-1.03

paio

-1.02

ovies

-1.02

angelo

-1.00

nikov

-1.00

osaurus

-1.00

reau

-0.98

POSITIVE LOGITS

 guiName

1.39

 Territories

1.21

Eff

1.17

Fem

1.14

Af

1.11

 Registry

1.09

Memory

1.09

 Selection

1.09

 Lines

1.08

 Transparency

1.07

Activations Density 0.032%

terms related to various types of "un" prefixes or organizations

No Comments

No Known Activations