INDEX

Explanations

sections of the document with no relevant content

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Spoljašnje

-0.61

 Opium

-0.53

 Euse

-0.52

ultier

-0.50

Vgl

-0.49

 hiperten

-0.48

 cáncer

-0.48

 computerized

-0.47

 opium

-0.47

 Mundi

-0.47

POSITIVE LOGITS

SourceChecksum

1.09

expandindo

1.06

 Roskov

0.76

ResumeLayout

0.68

InjectAttribute

0.66

AxisAlignment

0.66

المكان

0.65

rungsseite

0.64

شهاد

0.64

Tikang

0.60

Activations Density 0.016%

sections of the document with no relevant content

No Comments

No Known Activations