INDEX

Explanations

words related to consensus and collective agreement

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.08

1:0.09

2:0.08

3:0.08

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 lifes

-2.92

 Governors

-2.77

 Gork

-2.35

ween

-2.35

+++

-2.33

giving

-2.33

 Kinder

-2.30

 ende

-2.30

bryce

-2.27

 Godd

-2.19

POSITIVE LOGITS

apore

2.96

RFC

2.83

pc

2.65

PF

2.62

Mu

2.58

 Pikachu

2.53

��

2.50

ono

2.49

uria

2.46

Browser

2.45

Activations Density 0.000%

words related to consensus and collective agreement

No Comments

No Known Activations