INDEX

Explanations

conjunctions that connect ideas or phrases

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

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

ilateral

-2.71

 Telesc

-2.67

eas

-2.60

 grou

-2.53

 refuel

-2.52

�

-2.49

 Resolution

-2.49

 PowerPoint

-2.48

 Sequ

-2.46

 subp

-2.45

POSITIVE LOGITS

 Flesh

3.05

ModLoader

3.05

 Essence

2.92

hemy

2.84

Init

2.83

 Init

2.83

 blasphemy

2.80

 daemon

2.74

Sin

2.64

Hat

2.64

Activations Density 0.000%

conjunctions that connect ideas or phrases

No Comments

No Known Activations