INDEX

Explanations

occurrences of the character 'e' in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.4.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

localctx

-0.72

NewUrlParser

-0.69

 MessageBoxIcon

-0.63

jspx

-0.56

 ExecuteAsync

-0.55

 AppCompat

-0.55

FormTagHelper

-0.54

parseDouble

-0.54

 Undeclared

-0.54

 Carried

-0.53

POSITIVE LOGITS

 propOrder

0.58

SharedCtor

0.54

zość

0.49

fortawesome

0.49

AutoresizingMask

0.48

 ujednoznacz

0.47

RenderAtEndOf

0.46

ایج

0.44

 gezogen

0.44

 ComVisible

0.43

Activations Density 0.010%

occurrences of the character 'e' in the text

No Comments

No Known Activations