INDEX

Explanations

phrases related to descriptions and characteristics of various subjects, particularly focusing on the contrasts between outward appearances and internal qualities

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.07

1:0.03

2:0.08

3:0.08

4:0.10

5:0.06

6:0.02

7:0.38

8:0.03

9:0.02

10:0.03

11:0.04

Negative Logits

 respectively

-3.29

�

-2.85

aturday

-2.78

 portfolios

-2.64

iffe

-2.49

HAEL

-2.46

Their

-2.45

arios

-2.44

BLIC

-2.42

 Moroc

-2.34

POSITIVE LOGITS

Its

6.90

its

6.74

Its

6.59

ITS

4.62

its

4.43

 itself

4.43

it

4.05

It

3.02

 nutshell

2.73

pires

2.63

Activations Density 1.403%

phrases related to descriptions and characteristics of various subjects, particularly focusing on the contrasts between outward appearances and internal qualities

No Comments

No Known Activations