INDEX

Explanations

mentions of specific places or entities associated with actions or outcomes

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

0:0.05

1:0.02

2:0.14

3:0.06

4:0.14

5:0.07

6:0.02

7:0.02

8:0.23

9:0.12

10:0.04

11:0.03

Negative Logits

wordpress

-1.31

️

-1.17

 Gujar

-1.15

osexual

-1.14

llo

-1.14

 advoc

-1.07

 shaved

-1.07

��

-1.04

dump

-1.03

aiman

-1.02

POSITIVE LOGITS

ordes

1.45

aez

1.28

entials

1.25

phia

1.19

ioxide

1.19

 Pieces

1.14

ensibly

1.10

enhagen

1.04

 Newton

1.04

 Territory

1.03

Activations Density 0.005%

mentions of specific places or entities associated with actions or outcomes

No Comments

No Known Activations