INDEX

Explanations

references to institutions and entities that represent public interest and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 ModelExpression

-0.97

 pleaſure

-0.90

 themſelves

-0.88

 MonoBehaviour

-0.86

PreferredItem

-0.85

出版年

-0.79

 myſelf

-0.79

CWE

-0.79

IntoConstraints

-0.76

 itſelf

-0.75

POSITIVE LOGITS

our

0.72

tagHelperRunner

0.59

 наших

0.58

Our

0.57

our

0.54

Our

0.54

 nossa

0.52

 наши

0.52

 nossas

0.51

 nuestra

0.51

Activations Density 0.229%

references to institutions and entities that represent public interest and governance

No Comments

No Known Activations