INDEX

Explanations

tentative language and uncertainty in discussions

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

Autoritní

-0.66

 DIEGO

-0.53

нциклопедия

-0.53

[]:

-0.53

UnusedPrivate

-0.50

 iprot

-0.50

 accéder

-0.50

nanoTime

-0.49

 scolaires

-0.49

:]:

-0.49

POSITIVE LOGITS

Hozzáférés

0.54

InputBorder

0.54

fillType

0.50

GrantedAuthority

0.49

Насе

0.49

 pronunci

0.47

bnf

0.47

 catar

0.47

دانشنامهٔ

0.47

 undecided

0.47

Activations Density 0.240%

tentative language and uncertainty in discussions

No Comments

No Known Activations