INDEX

Explanations

elements related to investigations and evidence in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 AssemblyTitle

-0.58

 virtù

-0.54

 lyder

-0.51

antMatchers

-0.50

chema

-0.49

 seleção

-0.49

foque

-0.48

merate

-0.48

Хочу

-0.48

 plezier

-0.48

POSITIVE LOGITS

 contacted

0.69

 inconclusive

0.68

 deduced

0.65

 suspected

0.64

 suspect

0.62

 hypothesis

0.60

tagHelperRunner

0.60

 investigating

0.60

 concluded

0.60

investig

0.59

Activations Density 0.315%

elements related to investigations and evidence in a narrative context

No Comments

No Known Activations