INDEX

Explanations

structured data patterns, particularly within programming or data manipulation contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ázaro

-0.55

chenk

-0.53

orini

-0.50

deutschen

-0.49

vägen

-0.48

iddhar

-0.48

 суб

-0.48

sub

-0.47

 success

-0.47

kaw

-0.46

POSITIVE LOGITS

 AssemblyCulture

0.96

 protoimpl

0.92

 Normdatei

0.88

 ErrIntOverflow

0.84

المناصب

0.83

AnchorStyles

0.82

InitVars

0.82

IVEREF

0.81

parsedMessage

0.81

MigrationBuilder

0.78

Activations Density 0.318%

structured data patterns, particularly within programming or data manipulation contexts

No Comments

No Known Activations