INDEX

Explanations

mathematical notation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

pas

-0.51

 незавершена

-0.47

pas

-0.46

 base

-0.45

цездатний

-0.45

 passi

-0.44

SPATH

-0.44

 giao

-0.44

InputBorder

-0.44

Портал

-0.42

POSITIVE LOGITS

simpleType

0.68

StoreMessageInfo

0.67

</>

0.66

ContentAsync

0.66

ựng

0.63

Tikang

0.63

InitVars

0.61

scaffold

0.58

SequentialGroup

0.56

onResume

0.56

Activations Density 0.789%

mathematical notation and symbols

No Comments

No Known Activations