INDEX

Explanations

phrases that indicate relationships between conditions, trade-offs, and outcomes in various 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Referanser

-0.63

+#+#

-0.62

 nakalista

-0.57

uxxxx

-0.57

RTEE

-0.56

Portail

-0.51

tvguidetime

-0.51

 anledning

-0.49

তথ্যসূত্র

-0.47

 titolata

-0.47

POSITIVE LOGITS

 also

0.65

 همچنین

0.64

 results

0.61

cshtml

0.56

結果は

0.54

เลข

0.54

is

0.53

 numberOfRows

0.53

span

0.53

 außerdem

0.52

Activations Density 0.587%

phrases that indicate relationships between conditions, trade-offs, and outcomes in various contexts

No Comments

No Known Activations