INDEX

Explanations

phrases indicating exclusivity or uniqueness

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

0:0.09

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

 Armored

-3.05

 Mankind

-2.56

 Royale

-2.53

 photograph

-2.51

 rive

-2.49

MAT

-2.48

IUM

-2.45

GP

-2.41

 biome

-2.39

 possibly

-2.33

POSITIVE LOGITS

dq

2.90

ksh

2.60

eka

2.59

Cho

2.50

Esc

2.50

ventures

2.46

Dek

2.45

龍契士

2.45

ayne

2.45

 neighb

2.42

Activations Density 0.000%

phrases indicating exclusivity or uniqueness

No Comments

No Known Activations