INDEX

Explanations

the initials or single letters that are directly significant or used as classifications in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

��

-3.14

ワン

-3.08

��

-2.95

 carbohyd

-2.86

_-

-2.75

�

-2.73

OHN

-2.71

 VIDEOS

-2.70

RAM

-2.64

ById

-2.64

POSITIVE LOGITS

 Marg

2.67

Tad

2.60

Eg

2.53

 Liberties

2.45

Ecc

2.45

 Wellington

2.37

Gin

2.36

 democracies

2.36

arag

2.36

Soc

2.35

Activations Density 0.000%

the initials or single letters that are directly significant or used as classifications in the text

No Comments

No Known Activations