INDEX

Explanations

phrases related to memory and recollection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Portail

-0.56

 onOptions

-0.54

ApiOperation

-0.53

OGND

-0.52

astify

-0.48

ɕ

-0.48

प्त

-0.48

openConnection

-0.47

Geografie

-0.45

writeln

-0.45

POSITIVE LOGITS

 memory

3.32

 remember

3.00

 remembering

2.89

 remembered

2.83

 remembers

2.82

memory

2.77

 Memory

2.73

remember

2.69

 memories

2.68

 recall

2.64

Activations Density 0.419%

phrases related to memory and recollection

No Comments

No Known Activations