INDEX

Explanations

references to specific locations or places

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.08

6:0.09

7:0.08

8:0.07

9:0.09

10:0.07

11:0.06

Negative Logits

CRIP

-3.49

��

-3.33

][

-3.10

quished

-3.10

hovah

-3.09

 expr

-3.06

ario

-3.02

��

-2.93

iov

-2.89

aughs

-2.85

POSITIVE LOGITS

 Berry

2.98

 Wheeler

2.81

Kel

2.71

 Neal

2.71

 Cliff

2.70

 Clayton

2.68

TL

2.62

 Hank

2.61

Lew

2.60

 Clapper

2.51

Activations Density 0.000%

references to specific locations or places

No Comments

No Known Activations