INDEX

Explanations

instances of the word "named" and related variants

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

parsedMessage

-0.71

+#+

-0.69

 AssemblyProduct

-0.69

providedIn

-0.65

DialogContent

-0.64

λίου

-0.62

LabelTagHelper

-0.62

Geplaatst

-0.62

MessageTagHelper

-0.60

expandindo

-0.60

POSITIVE LOGITS

 naming

2.09

 Naming

1.94

 named

1.80

naming

1.66

named

1.64

 name

1.64

Naming

1.61

 Named

1.60

 names

1.56

 Name

1.54

Activations Density 0.146%

instances of the word "named" and related variants

No Comments

No Known Activations