INDEX

Explanations

the presence of the abbreviation "St" which often refers to "Saint" or "Street" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

layui

-0.95

ագրություններ

-0.88

MIM

-0.85

 Theſe

-0.82

UrlResolution

-0.82

Geplaatst

-0.81

 bParam

-0.81

Kauf

-0.81

 Naran

-0.80

urlopen

-0.80

POSITIVE LOGITS

St

2.35

St

2.10

st

1.90

 Saint

1.43

Saint

1.31

ST

1.31

st

1.28

 SAINT

1.24

 saint

1.14

saint

1.14

Activations Density 0.043%

the presence of the abbreviation "St" which often refers to "Saint" or "Street" in various contexts

No Comments

No Known Activations