INDEX

Explanations

names of fictional characters and entities, particularly in the context of entertainment or media

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.59

chauung

-0.50

twimg

-0.44

ország

-0.42

migrationBuilder

-0.41

 القدم

-0.40

non

-0.40

gegangen

-0.40

got

-0.40

big

-0.39

POSITIVE LOGITS

 صوتيه

0.82

 transférez

0.82

хьтан

0.82

 فريبيس

0.78

 समीक्षक

0.74

ActionCreators

0.73

 otomatig

0.72

PyExc

0.72

tvguidetime

0.71

 GenerationType

0.71

Activations Density 0.313%

names of fictional characters and entities, particularly in the context of entertainment or media

No Comments

No Known Activations