INDEX

Explanations

the presence of initial tokens in a document, possibly indicating the start of different segments or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

ponses

-0.77

 propOrder

-0.64

</tfoot>

-0.59

tanleria

-0.58

 huéspedes

-0.58

 Waray

-0.57

 ExecuteAsync

-0.57

Santis

-0.55

Filmografia

-0.55

 reminders

-0.55

POSITIVE LOGITS

 nahilalakip

0.57

WebVitals

0.52

expandindo

0.51

 برانيه

0.51

 pinulongan

0.49

numerusform

0.48

 getopt

0.47

 متعلقه

0.46

EndTag

0.45

 Palme

0.45

Activations Density 0.236%

the presence of initial tokens in a document, possibly indicating the start of different segments or sections

No Comments

No Known Activations