INDEX

Explanations

sentences related to actions or events involving writing or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 برانيه

-0.52

albeit

-0.49

Lmfao

-0.46

 farlo

-0.45

 signifikan

-0.45

ViewChild

-0.45

NOPE

-0.43

 лока

-0.43

 arguably

-0.43

 utilizing

-0.42

POSITIVE LOGITS

 InputDecoration

0.75

UnknownFields

0.68

DropTable

0.67

Revenir

0.65

onViewCreated

0.65

 ganglion

0.60

 الدولى

0.60

parsedMessage

0.59

ErrorListener

0.59

 estekak

0.58

Activations Density 0.217%

sentences related to actions or events involving writing or communication

No Comments

No Known Activations