INDEX

Explanations

expressions of previous assumptions or beliefs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Alike

-0.45

 للمعارف

-0.44

 SqlCommand

-0.44

}{*}{

-0.41

ச்ச

-0.40

AndEndTag

-0.40

manteau

-0.40

 sensação

-0.40

 OnInit

-0.39

 îns

-0.38

POSITIVE LOGITS

Erreferentziak

0.79

 propOrder

0.72

Varint

0.66

printStats

0.65

 bağlantılar

0.60

ttemberg

0.60

 ErrIntOverflow

0.60

ثيق

0.59

ندران

0.58

LayoutConstraint

0.57

Activations Density 0.218%

expressions of previous assumptions or beliefs

No Comments

No Known Activations