INDEX

Explanations

phrases indicating future possibilities or anticipated events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.01

2:0.13

3:0.05

4:0.13

5:0.02

6:0.03

7:0.37

8:0.02

9:0.03

10:0.06

11:0.08

Negative Logits

oqu

-1.75

mouth

-1.53

 apologised

-1.44

 guiActive

-1.44

 joked

-1.44

boro

-1.42

 apologized

-1.41

 nicknamed

-1.38

 nickname

-1.34

rex

-1.30

POSITIVE LOGITS

 viability

1.51

abil

1.49

 salvation

1.45

 Pascal

1.44

nesota

1.37

 probabilities

1.36

 sanity

1.31

 Sparks

1.30

 elusive

1.30

Activations Density 0.001%

phrases indicating future possibilities or anticipated events

No Comments

No Known Activations