INDEX

Explanations

technical terms related to investigation parameters and methods

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

followed by "of," "to," "or," "and," or "."

np_acts-logits-general · gemini-2.0-flash

expanding on nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

flink

-0.69

 Meksiku

-0.64

 TextAppearance

-0.64

قایناقلار

-0.62

onViewCreated

-0.60

Jeografia

-0.56

BIDDEN

-0.55

 isInitialized

-0.53

fopen

-0.53

AnimationsModule

-0.52

POSITIVE LOGITS

 drastically

0.59

 dramatically

0.56

 considerably

0.56

 Púb

0.53

 significantly

0.53

 substantially

0.52

 tercio

0.51

 slightly

0.49

 radically

0.48

AccessorTable

0.47

Activations Density 0.633%

technical terms related to investigation parameters and methods

followed by "of," "to," "or," "and," or "."

expanding on nouns

No Comments

No Known Activations