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

0:0.08

1:0.07

2:0.07

3:0.09

4:0.07

5:0.09

6:0.09

7:0.08

8:0.07

9:0.09

10:0.07

11:0.09

Negative Logits

JV

-2.84

ENC

-2.78

XM

-2.74

Sax

-2.73

UV

-2.69

 Krypt

-2.65

crop

-2.63

VT

-2.62

 Cain

-2.62

UTION

-2.59

POSITIVE LOGITS

 reapp

2.69

 Spotlight

2.67

 Splash

2.49

�

2.48

 estim

2.47

 plun

2.45

 commemor

2.43

 drawer

2.38

 tracker

2.37

 Finder

2.35

Activations Density 0.000%

the letter "Q"

No Comments

No Known Activations