INDEX

Explanations

the letter "Q"

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

1:0.07

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.08

8:0.09

9:0.07

10:0.08

11:0.09

Negative Logits

 Sensor

-3.02

NZ

-3.00

NP

-2.85

 mast

-2.81

 Meta

-2.81

 Mech

-2.79

 Sale

-2.79

 Admir

-2.73

 Whale

-2.64

 Nanto

-2.64

POSITIVE LOGITS

hower

3.10

interstitial

2.97

 Jindal

2.73

ISIS

2.69

2.63

ogan

2.63

Georgia

2.63

Secretary

2.57

edu

2.56

Louis

2.55

Activations Density 0.000%

the letter "Q"

No Comments

No Known Activations