INDEX

Explanations

character names and references in dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 архивлан

-0.55

tagens

-0.54

łgorzata

-0.53

unesse

-0.51

HasAnnotation

-0.50

 transfieras

-0.50

 समीक्षाएं

-0.49

iliar

-0.47

flage

-0.47

льников

-0.47

POSITIVE LOGITS

Doc

0.66

Doc

0.62

 Smit

0.60

 Brownie

0.57

 Short

0.56

 Little

0.55

 fatty

0.55

Smit

0.55

 Normdatei

0.55

 Fatty

0.55

Activations Density 0.201%

character names and references in dialogue

No Comments

No Known Activations