INDEX

Explanations

programming constructs related to trial and error processes in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

::_('

-0.56

 referenties

-0.55

 שוליים

-0.55

GHIJKLM

-0.53

MigrationBuilder

-0.52

MessageTagHelper

-0.52

talk

-0.47

PointerException

-0.47

orghe

-0.47

contentLoaded

-0.47

POSITIVE LOGITS

 repetition

0.70

 repetitions

0.69

Hentet

0.66

 répé

0.62

 repeated

0.61

 AssemblyTitle

0.60

 وتسجيلات

0.60

 repeatable

0.58

repe

0.57

petitive

0.57

Activations Density 0.533%

programming constructs related to trial and error processes in code snippets

No Comments

No Known Activations