INDEX

Explanations

references to a significant decrease or downfall

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

1:0.09

2:0.07

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 buyers

-3.11

apolis

-3.09

inventory

-2.67

invest

-2.66

ullivan

-2.64

Gur

-2.60

 purchases

-2.51

bid

-2.50

 arbit

-2.49

ommel

-2.47

POSITIVE LOGITS

 Reflex

2.88

;;;;

2.74

 Technique

2.70

!/

2.66

 Logo

2.60

�

2.59

ÃÂ

2.54

 Rhythm

2.53

 Keyboard

2.48

 enthusi

2.47

Activations Density 0.000%

references to a significant decrease or downfall

No Comments

No Known Activations