INDEX

Explanations

biographical details about individuals, particularly focusing on their life events and accomplishments

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

Follows verbs "worked," "served," or start of turn

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 dodgy

-0.47

 вроде

-0.46

 EconPapers

-0.46

 mainstream

-0.45

">//

-0.44

 Islamist

-0.44

Jegyzetek

-0.43

 consultancy

-0.43

Искәрмәләр

-0.43

Lähteet

-0.43

POSITIVE LOGITS

 predeceased

0.62

extAlignment

0.60

 lovingly

0.60

 loving

0.57

later

0.56

 later

0.54

Ehrungen

0.52

 loved

0.51

 lifelong

0.50

 senere

0.50

Activations Density 0.054%

biographical details about individuals, particularly focusing on their life events and accomplishments

Follows verbs "worked," "served," or start of turn

No Comments

No Known Activations