INDEX

Explanations

phrases related to financial responsibility or accountability

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.06

1:0.07

2:0.22

3:0.05

4:0.05

5:0.04

6:0.05

7:0.07

8:0.05

9:0.05

10:0.18

11:0.06

Negative Logits

maxwell

-3.04

atis

-2.98

ilateral

-2.92

alys

-2.87

ould

-2.79

vier

-2.75

uti

-2.70

reat

-2.65

£

-2.63

oeuv

-2.63

POSITIVE LOGITS

Me

2.94

 Meyer

2.52

Neb

2.41

EW

2.36

 Sans

2.35

 Noir

2.32

 Megan

2.25

Gel

2.24

 Ober

2.23

 Jenner

2.19

Activations Density 0.000%

phrases related to financial responsibility or accountability

No Comments

No Known Activations