INDEX

Explanations

references to characters and their relationships in narrative contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

clinical operations Anton Brain

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

UrlResolution

-0.67

principalTable

-0.51

 ffilmiau

-0.45

hyrchwyd

-0.45

-0.43

Související

-0.43

 gezicht

-0.43

 BoxFit

-0.43

MethodImpl

-0.43

 hObject

-0.43

POSITIVE LOGITS

CreateMap

0.52

 jspb

0.43

expandindo

0.35

tableFuture

0.33

spół

0.33

 Roskov

0.32

 mergeFrom

0.32

endmodule

0.31

withIdentifier

0.31

ürme

0.31

Activations Density 0.213%

references to characters and their relationships in narrative contexts

clinical operations Anton Brain

No Comments

No Known Activations