INDEX

Explanations

words indicating proximity or relationships in terms of location or amount

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.03

1:0.03

2:0.14

3:0.17

4:0.35

5:0.05

6:0.02

7:0.02

8:0.04

9:0.06

10:0.03

11:0.02

Negative Logits

ahime

-1.46

nect

-1.37

onite

-1.35

 Accessed

-1.32

BIL

-1.29

 stewards

-1.27

vern

-1.24

NSA

-1.21

rane

-1.19

stal

-1.19

POSITIVE LOGITS

 whatsoever

1.44

else

1.40

ゴン

1.34

 totality

1.34

ooo

1.34

away

1.32

oway

1.31

asia

1.31

 subdivision

1.29

perty

1.28

Activations Density 0.007%

words indicating proximity or relationships in terms of location or amount

No Comments

No Known Activations