INDEX

Explanations

phrases indicating consensus or agreement among groups of people or stakeholders

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_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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.01

2:0.07

3:0.05

4:0.11

5:0.03

6:0.03

7:0.40

8:0.02

9:0.03

10:0.11

11:0.09

Negative Logits

 Shutterstock

-1.52

Lif

-1.51

ortun

-1.47

ificial

-1.40

amon

-1.37

bucks

-1.36

reon

-1.33

ा

-1.33

lux

-1.33

 Lent

-1.32

POSITIVE LOGITS

 opinion

1.65

 consensus

1.64

 unanimous

1.62

 unanimously

1.54

�

1.53

wcsstore

1.47

 opin

1.41

REDACTED

1.38

 unanim

1.37

UGC

1.36

Activations Density 0.009%

phrases indicating consensus or agreement among groups of people or stakeholders

No Comments

No Known Activations