INDEX

Explanations

terms related to processes and measurements in a technical or scientific context

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

 εικό

-0.57

Спољашње

-0.56

 ſever

-0.56

 habet

-0.54

AnchorStyles

-0.53

 thiệu

-0.53

StoryboardSegue

-0.52

 pleaſure

-0.51

 houſe

-0.51

 tranſ

-0.50

POSITIVE LOGITS

0.94

0.92

$\

0.89

0.88

0.87

0.86

0.85

λ

0.85

0.84

Activations Density 4.806%

terms related to processes and measurements in a technical or scientific context

No Comments

No Known Activations