INDEX

Explanations

the definite article "the"

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

2:0.08

3:0.06

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.10

10:0.09

11:0.09

Negative Logits

bidden

-1.68

 GOODMAN

-1.58

 Transfer

-1.56

 Diagn

-1.56

 palp

-1.44

anton

-1.40

 Touch

-1.40

stop

-1.37

 suspend

-1.36

 Caption

-1.35

POSITIVE LOGITS

sburg

1.97

 strongh

1.67

ilian

1.58

hus

1.57

OV

1.55

iphate

1.54

ovi

1.53

Sov

1.52

 Janeiro

1.47

opolis

1.45

Activations Density 0.000%

the definite article "the"

No Comments

No Known Activations