INDEX

Explanations

occurrences of the variable 'i' in iterative contexts like loops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

WithIOException

-0.63

 estekak

-0.56

########.

-0.55

InitVars

-0.53

+#+

-0.52

DebuggerStep

-0.52

Xna

-0.51

 Same

-0.50

unknownFields

-0.49

POSITIVE LOGITS

 تضيفلها

0.71

 CreateTagHelper

0.71

UserScript

0.65

StoryboardSegue

0.65

 Bourgoin

0.62

++)

0.62

tisgarh

0.59

 AdapterView

0.57

batore

0.57

acular

0.55

Activations Density 0.009%

occurrences of the variable 'i' in iterative contexts like loops

No Comments

No Known Activations