INDEX

Explanations

the word "imagine" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

DebuggerNonUser

-0.63

Imagine

-0.60

 विश्वसनीयता

-0.57

 للمعارف

-0.57

 Imagine

-0.56

 vincere

-0.55

 <>",

-0.55

SharedDtor

-0.55

 serge

-0.55

openSession

-0.53

POSITIVE LOGITS

nitus

0.83

edly

0.67

agog

0.64

pertino

0.63

 dàng

0.62

 Portail

0.60

tualmente

0.60

eraard

0.60

DoubleQuotes

0.60

guous

0.59

Activations Density 0.024%

the word "imagine" in various contexts

No Comments

No Known Activations